Skip to content

Listings

All listings: Amazon Web Services

Every listing for the models on page 1 of 9 of Amazon Web Services, including each model's other versions and routes. Back to Amazon Web Services

Sold by Amazon Web Services

169 listings on this page sold by Amazon Web Services.

Select a score for details.

About these columns
llminfo IQ
llminfo IQ (capability index). How llminfo IQ is computed
Coding IQ
llminfo Coding IQ (coding capability, its own scale). How Coding IQ is computed
Value
Value for money. 50 means as expected for its results. Above 50, cheaper per task. How Value for money works
Yap
Tokens used per coding task vs. models with the same results. Includes agents that write code. Chattiness on maths doesn't predict it. How the Yap score works
Modelllminfo IQCoding IQInput $/1MOutput $/1MMax Input TokensValueYapEpoch Capabilities Index
Claude Fable 5.2
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
New
Released 9 Nov 2026
anthropic.claude-fable-5-2
149.0
From 171 benchmarks. Plenty of data behind it.
147 ±11
Coding IQ 146.6, 95% interval 135–158. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$8.00cache read $0.20$40.00cache write $10.001M
73.1
Good value (73.1). Cheaper per task than its benchmark results predict. Plenty of data behind it.
44 ±9
Terse (44 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
173.4
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Fable 5.2
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
New
Released 9 Nov 2026
eu.anthropic.claude-fable-5-2 · 🇪🇺 eu
149.0
From 171 benchmarks. Plenty of data behind it.
147 ±11
Coding IQ 146.6, 95% interval 135–158. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$8.80cache read $0.22$44.00cache write $11.001M
73.1
Good value (73.1). Cheaper per task than its benchmark results predict. Plenty of data behind it.
44 ±9
Terse (44 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
173.4
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Fable 5.2
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
New
Released 9 Nov 2026
global.anthropic.claude-fable-5-2 · global
149.0
From 171 benchmarks. Plenty of data behind it.
147 ±11
Coding IQ 146.6, 95% interval 135–158. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$8.00cache read $0.20$40.00cache write $10.001M
73.1
Good value (73.1). Cheaper per task than its benchmark results predict. Plenty of data behind it.
44 ±9
Terse (44 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
173.4
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Fable 5.2
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
New
Released 9 Nov 2026
us-gov.anthropic.claude-fable-5-2 · 🇺🇸 us-gov
149.0
From 171 benchmarks. Plenty of data behind it.
147 ±11
Coding IQ 146.6, 95% interval 135–158. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$9.60cache read $0.24$48.00cache write $12.001M
73.1
Good value (73.1). Cheaper per task than its benchmark results predict. Plenty of data behind it.
44 ±9
Terse (44 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
173.4
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Fable 5.2
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
New
Released 9 Nov 2026
us.anthropic.claude-fable-5-2 · 🇺🇸 us
149.0
From 171 benchmarks. Plenty of data behind it.
147 ±11
Coding IQ 146.6, 95% interval 135–158. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$8.80cache read $0.22$44.00cache write $11.001M
73.1
Good value (73.1). Cheaper per task than its benchmark results predict. Plenty of data behind it.
44 ±9
Terse (44 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
173.4
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Fable 5.2
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
New
Released 9 Nov 2026
eu.anthropic.claude-fable-5-2-v1 · 🇪🇺 eu
149.0
From 171 benchmarks. Plenty of data behind it.
147 ±11
Coding IQ 146.6, 95% interval 135–158. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$8.80$44.00Not published by the provider
73.1
Good value (73.1). Cheaper per task than its benchmark results predict. Plenty of data behind it.
44 ±9
Terse (44 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
173.4
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Fable 5.2
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
New
Released 9 Nov 2026
global.anthropic.claude-fable-5-2-v1 · global
149.0
From 171 benchmarks. Plenty of data behind it.
147 ±11
Coding IQ 146.6, 95% interval 135–158. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$8.00$40.00Not published by the provider
73.1
Good value (73.1). Cheaper per task than its benchmark results predict. Plenty of data behind it.
44 ±9
Terse (44 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
173.4
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Fable 5.2
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
New
Released 9 Nov 2026
us.anthropic.claude-fable-5-2-v1 · 🇺🇸 us
149.0
From 171 benchmarks. Plenty of data behind it.
147 ±11
Coding IQ 146.6, 95% interval 135–158. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$8.80$44.00Not published by the provider
73.1
Good value (73.1). Cheaper per task than its benchmark results predict. Plenty of data behind it.
44 ±9
Terse (44 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
173.4
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Fable 5.2
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
New
Released 9 Nov 2026
anthropic.claude-fable-5-2-v1
149.0
From 171 benchmarks. Plenty of data behind it.
147 ±11
Coding IQ 146.6, 95% interval 135–158. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$8.00$40.00Not published by the provider
73.1
Good value (73.1). Cheaper per task than its benchmark results predict. Plenty of data behind it.
44 ±9
Terse (44 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
173.4
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-6.2 Astra
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
New
Released 17 Nov 2026
openai.gpt-6.2-astra
148.3
From 120 benchmarks. Plenty of data behind it.
142 ±9
Coding IQ 141.7, 95% interval 133–150. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$8.80cache read $0.44$44.00cache write $11.00922K
66.9
Good value (66.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
48 ±9
Typical (48 ±9). Generates about as many tokens as models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate.
172.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-6.2 Astra
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
New
Released 17 Nov 2026
global.openai.gpt-6.2-astra · global
148.3
From 120 benchmarks. Plenty of data behind it.
142 ±9
Coding IQ 141.7, 95% interval 133–150. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$8.00cache read $0.40$40.00cache write $10.00922K
66.9
Good value (66.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
48 ±9
Typical (48 ±9). Generates about as many tokens as models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate.
172.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-6.2 Astra
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
New
Released 17 Nov 2026
us.openai.gpt-6.2-astra · 🇺🇸 us
148.3
From 120 benchmarks. Plenty of data behind it.
142 ±9
Coding IQ 141.7, 95% interval 133–150. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$8.80cache read $0.44$44.00cache write $11.00922K
66.9
Good value (66.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
48 ±9
Typical (48 ±9). Generates about as many tokens as models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate.
172.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-6 Astra
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-6.2 AstraWe compared release dates and version names in our catalogue.
openai.gpt-6-astra
147.2
From 338 benchmarks. Plenty of data behind it.
139 ±6
Coding IQ 138.9, 95% interval 133–145. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$11.00cache read $1.10$55.00cache write $13.75922K
62.1
Good value (62.1). Cheaper per task than its benchmark results predict. Plenty of data behind it.
37 ±8
Terse (37 ±8). Generates fewer tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
169.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-6 Astra
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-6.2 AstraWe compared release dates and version names in our catalogue.
global.openai.gpt-6-astra · global
147.2
From 338 benchmarks. Plenty of data behind it.
139 ±6
Coding IQ 138.9, 95% interval 133–145. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$10.00cache read $1.00$50.00cache write $12.50922K
62.1
Good value (62.1). Cheaper per task than its benchmark results predict. Plenty of data behind it.
37 ±8
Terse (37 ±8). Generates fewer tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
169.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-6 Astra
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-6.2 AstraWe compared release dates and version names in our catalogue.
us.openai.gpt-6-astra · 🇺🇸 us
147.2
From 338 benchmarks. Plenty of data behind it.
139 ±6
Coding IQ 138.9, 95% interval 133–145. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$11.00cache read $1.10$55.00cache write $13.75922K
62.1
Good value (62.1). Cheaper per task than its benchmark results predict. Plenty of data behind it.
37 ±8
Terse (37 ±8). Generates fewer tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
169.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-6 Astra
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-6.2 AstraWe compared release dates and version names in our catalogue.
eu.openai.gpt-6-astra · 🇪🇺 eu
147.2
From 338 benchmarks. Plenty of data behind it.
139 ±6
Coding IQ 138.9, 95% interval 133–145. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$10.00$50.00Not published by the provider
62.1
Good value (62.1). Cheaper per task than its benchmark results predict. Plenty of data behind it.
37 ±8
Terse (37 ±8). Generates fewer tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
169.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 5.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
anthropic.claude-opus-5-5
146.6
From 329 benchmarks. Plenty of data behind it.
147 ±5
Coding IQ 147.1, 95% interval 142–152. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$4.00cache read $0.20$20.00cache write $5.001M
66.8
Good value (66.8). Cheaper per task than its benchmark results predict. Plenty of data behind it.
65 ±12
Chatty (65 ±12). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
168.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 5.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
apac.anthropic.claude-opus-5-5 · apac
146.6
From 329 benchmarks. Plenty of data behind it.
147 ±5
Coding IQ 147.1, 95% interval 142–152. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$4.40cache read $0.22$22.00cache write $5.501M
66.8
Good value (66.8). Cheaper per task than its benchmark results predict. Plenty of data behind it.
65 ±12
Chatty (65 ±12). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
168.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 5.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
au.anthropic.claude-opus-5-5 · 🇦🇺 au
146.6
From 329 benchmarks. Plenty of data behind it.
147 ±5
Coding IQ 147.1, 95% interval 142–152. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$4.40cache read $0.22$22.00cache write $5.501M
66.8
Good value (66.8). Cheaper per task than its benchmark results predict. Plenty of data behind it.
65 ±12
Chatty (65 ±12). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
168.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 5.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
eu.anthropic.claude-opus-5-5 · 🇪🇺 eu
146.6
From 329 benchmarks. Plenty of data behind it.
147 ±5
Coding IQ 147.1, 95% interval 142–152. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$4.40cache read $0.22$22.00cache write $5.501M
66.8
Good value (66.8). Cheaper per task than its benchmark results predict. Plenty of data behind it.
65 ±12
Chatty (65 ±12). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
168.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 5.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
global.anthropic.claude-opus-5-5 · global
146.6
From 329 benchmarks. Plenty of data behind it.
147 ±5
Coding IQ 147.1, 95% interval 142–152. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$4.00cache read $0.20$20.00cache write $5.001M
66.8
Good value (66.8). Cheaper per task than its benchmark results predict. Plenty of data behind it.
65 ±12
Chatty (65 ±12). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
168.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 5.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
jp.anthropic.claude-opus-5-5 · 🇯🇵 jp
146.6
From 329 benchmarks. Plenty of data behind it.
147 ±5
Coding IQ 147.1, 95% interval 142–152. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$4.40cache read $0.22$22.00cache write $5.501M
66.8
Good value (66.8). Cheaper per task than its benchmark results predict. Plenty of data behind it.
65 ±12
Chatty (65 ±12). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
168.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 5.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
us-gov.anthropic.claude-opus-5-5 · 🇺🇸 us-gov
146.6
From 329 benchmarks. Plenty of data behind it.
147 ±5
Coding IQ 147.1, 95% interval 142–152. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$4.80cache read $0.24$24.00cache write $6.001M
66.8
Good value (66.8). Cheaper per task than its benchmark results predict. Plenty of data behind it.
65 ±12
Chatty (65 ±12). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
168.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 5.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
us.anthropic.claude-opus-5-5 · 🇺🇸 us
146.6
From 329 benchmarks. Plenty of data behind it.
147 ±5
Coding IQ 147.1, 95% interval 142–152. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$4.40cache read $0.22$22.00cache write $5.501M
66.8
Good value (66.8). Cheaper per task than its benchmark results predict. Plenty of data behind it.
65 ±12
Chatty (65 ±12). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
168.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 5.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
au.anthropic.claude-opus-5-5-v1 · 🇦🇺 au
146.6
From 329 benchmarks. Plenty of data behind it.
147 ±5
Coding IQ 147.1, 95% interval 142–152. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$4.40$22.00Not published by the provider
66.8
Good value (66.8). Cheaper per task than its benchmark results predict. Plenty of data behind it.
65 ±12
Chatty (65 ±12). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
168.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 5.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
eu.anthropic.claude-opus-5-5-v1 · 🇪🇺 eu
146.6
From 329 benchmarks. Plenty of data behind it.
147 ±5
Coding IQ 147.1, 95% interval 142–152. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$4.40$22.00Not published by the provider
66.8
Good value (66.8). Cheaper per task than its benchmark results predict. Plenty of data behind it.
65 ±12
Chatty (65 ±12). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
168.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 5.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
global.anthropic.claude-opus-5-5-v1 · global
146.6
From 329 benchmarks. Plenty of data behind it.
147 ±5
Coding IQ 147.1, 95% interval 142–152. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$4.00$20.00Not published by the provider
66.8
Good value (66.8). Cheaper per task than its benchmark results predict. Plenty of data behind it.
65 ±12
Chatty (65 ±12). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
168.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 5.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
jp.anthropic.claude-opus-5-5-v1 · 🇯🇵 jp
146.6
From 329 benchmarks. Plenty of data behind it.
147 ±5
Coding IQ 147.1, 95% interval 142–152. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$4.40$22.00Not published by the provider
66.8
Good value (66.8). Cheaper per task than its benchmark results predict. Plenty of data behind it.
65 ±12
Chatty (65 ±12). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
168.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 5.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
us.anthropic.claude-opus-5-5-v1 · 🇺🇸 us
146.6
From 329 benchmarks. Plenty of data behind it.
147 ±5
Coding IQ 147.1, 95% interval 142–152. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$4.40$22.00Not published by the provider
66.8
Good value (66.8). Cheaper per task than its benchmark results predict. Plenty of data behind it.
65 ±12
Chatty (65 ±12). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
168.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 5.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
anthropic.claude-opus-5-5-v1
146.6
From 329 benchmarks. Plenty of data behind it.
147 ±5
Coding IQ 147.1, 95% interval 142–152. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$4.00$20.00Not published by the provider
66.8
Good value (66.8). Cheaper per task than its benchmark results predict. Plenty of data behind it.
65 ±12
Chatty (65 ±12). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
168.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-6.1 Sol
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
openai.gpt-6.1-sol
145.6
From 239 benchmarks. Plenty of data behind it.
135 ±16
Coding IQ 135.0, 95% interval 119–151. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.20cache read $0.11$11.00cache write $2.751M
68.3
Good value (68.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
51 ±11
Typical (51 ±11). Generates about as many tokens as models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate.
168.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-6.1 Sol
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
global.openai.gpt-6.1-sol · global
145.6
From 239 benchmarks. Plenty of data behind it.
135 ±16
Coding IQ 135.0, 95% interval 119–151. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.10$10.00cache write $2.501M
68.3
Good value (68.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
51 ±11
Typical (51 ±11). Generates about as many tokens as models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate.
168.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-6.1 Sol
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
us.openai.gpt-6.1-sol · 🇺🇸 us
145.6
From 239 benchmarks. Plenty of data behind it.
135 ±16
Coding IQ 135.0, 95% interval 119–151. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.20cache read $0.11$11.00cache write $2.751M
68.3
Good value (68.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
51 ±11
Typical (51 ±11). Generates about as many tokens as models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate.
168.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Fable 5.1
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Fable 5.2We compared release dates and version names in our catalogue.
anthropic.claude-fable-5-1
145.3
From 253 benchmarks. Plenty of data behind it.
138 ±5
Coding IQ 137.9, 95% interval 133–143. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$10.00cache read $0.25$50.00cache write $12.501M
64.0
Good value (64.0). Cheaper per task than its benchmark results predict. Plenty of data behind it.
63 ±9
Chatty (63 ±9). Generates more tokens than models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate.
167.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Fable 5.1
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Fable 5.2We compared release dates and version names in our catalogue.
eu.anthropic.claude-fable-5-1 · 🇪🇺 eu
145.3
From 253 benchmarks. Plenty of data behind it.
138 ±5
Coding IQ 137.9, 95% interval 133–143. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$11.00cache read $0.275$55.00cache write $13.751M
64.0
Good value (64.0). Cheaper per task than its benchmark results predict. Plenty of data behind it.
63 ±9
Chatty (63 ±9). Generates more tokens than models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate.
167.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Fable 5.1
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Fable 5.2We compared release dates and version names in our catalogue.
global.anthropic.claude-fable-5-1 · global
145.3
From 253 benchmarks. Plenty of data behind it.
138 ±5
Coding IQ 137.9, 95% interval 133–143. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$10.00cache read $0.25$50.00cache write $12.501M
64.0
Good value (64.0). Cheaper per task than its benchmark results predict. Plenty of data behind it.
63 ±9
Chatty (63 ±9). Generates more tokens than models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate.
167.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Fable 5.1
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Fable 5.2We compared release dates and version names in our catalogue.
us-gov.anthropic.claude-fable-5-1 · 🇺🇸 us-gov
145.3
From 253 benchmarks. Plenty of data behind it.
138 ±5
Coding IQ 137.9, 95% interval 133–143. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$12.00cache read $0.30$60.00cache write $15.001M
64.0
Good value (64.0). Cheaper per task than its benchmark results predict. Plenty of data behind it.
63 ±9
Chatty (63 ±9). Generates more tokens than models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate.
167.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Fable 5.1
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Fable 5.2We compared release dates and version names in our catalogue.
us.anthropic.claude-fable-5-1 · 🇺🇸 us
145.3
From 253 benchmarks. Plenty of data behind it.
138 ±5
Coding IQ 137.9, 95% interval 133–143. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$11.00cache read $0.275$55.00cache write $13.751M
64.0
Good value (64.0). Cheaper per task than its benchmark results predict. Plenty of data behind it.
63 ±9
Chatty (63 ±9). Generates more tokens than models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate.
167.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Fable 5.1
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Fable 5.2We compared release dates and version names in our catalogue.
eu.anthropic.claude-fable-5-1-v1 · 🇪🇺 eu
145.3
From 253 benchmarks. Plenty of data behind it.
138 ±5
Coding IQ 137.9, 95% interval 133–143. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$11.00$55.00Not published by the provider
64.0
Good value (64.0). Cheaper per task than its benchmark results predict. Plenty of data behind it.
63 ±9
Chatty (63 ±9). Generates more tokens than models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate.
167.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Fable 5.1
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Fable 5.2We compared release dates and version names in our catalogue.
global.anthropic.claude-fable-5-1-v1 · global
145.3
From 253 benchmarks. Plenty of data behind it.
138 ±5
Coding IQ 137.9, 95% interval 133–143. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$10.00$50.00Not published by the provider
64.0
Good value (64.0). Cheaper per task than its benchmark results predict. Plenty of data behind it.
63 ±9
Chatty (63 ±9). Generates more tokens than models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate.
167.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Fable 5.1
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Fable 5.2We compared release dates and version names in our catalogue.
us.anthropic.claude-fable-5-1-v1 · 🇺🇸 us
145.3
From 253 benchmarks. Plenty of data behind it.
138 ±5
Coding IQ 137.9, 95% interval 133–143. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$11.00$55.00Not published by the provider
64.0
Good value (64.0). Cheaper per task than its benchmark results predict. Plenty of data behind it.
63 ±9
Chatty (63 ±9). Generates more tokens than models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate.
167.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Fable 5.1
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Fable 5.2We compared release dates and version names in our catalogue.
anthropic.claude-fable-5-1-v1
145.3
From 253 benchmarks. Plenty of data behind it.
138 ±5
Coding IQ 137.9, 95% interval 133–143. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$10.00$50.00Not published by the provider
64.0
Good value (64.0). Cheaper per task than its benchmark results predict. Plenty of data behind it.
63 ±9
Chatty (63 ±9). Generates more tokens than models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate.
167.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-6.2 Sol
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
openai.gpt-6.2-sol
144.3
From 104 benchmarks. Plenty of data behind it.
139 ±9
Coding IQ 139.0, 95% interval 130–148. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.20cache read $0.11$11.00cache write $2.75922K
69.3
Good value (69.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
48 ±9
Typical (48 ±9). Generates about as many tokens as models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate.
Not measured
GPT-6.2 Sol
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
global.openai.gpt-6.2-sol · global
144.3
From 104 benchmarks. Plenty of data behind it.
139 ±9
Coding IQ 139.0, 95% interval 130–148. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.10$10.00cache write $2.50922K
69.3
Good value (69.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
48 ±9
Typical (48 ±9). Generates about as many tokens as models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate.
Not measured
GPT-6.2 Sol
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
us.openai.gpt-6.2-sol · 🇺🇸 us
144.3
From 104 benchmarks. Plenty of data behind it.
139 ±9
Coding IQ 139.0, 95% interval 130–148. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.20cache read $0.11$11.00cache write $2.75922K
69.3
Good value (69.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
48 ±9
Typical (48 ±9). Generates about as many tokens as models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate.
Not measured
Claude Opus 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
anthropic.claude-opus-5
143.9
From 389 benchmarks. Plenty of data behind it.
134 ±6
Coding IQ 133.8, 95% interval 128–140. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.00cache read $0.50batch $2.50$25.00cache write $6.25batch $12.501M
64.6
Good value (64.6). Cheaper per task than its benchmark results predict. Plenty of data behind it.
61 ±9
Chatty (61 ±9). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
164.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
global.anthropic.claude-opus-5 · global
143.9
From 389 benchmarks. Plenty of data behind it.
134 ±6
Coding IQ 133.8, 95% interval 128–140. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.00cache read $0.50batch $2.50$25.00cache write $6.25batch $12.501M
64.6
Good value (64.6). Cheaper per task than its benchmark results predict. Plenty of data behind it.
61 ±9
Chatty (61 ±9). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
164.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
regional.anthropic.claude-opus-5 · regional
143.9
From 389 benchmarks. Plenty of data behind it.
134 ±6
Coding IQ 133.8, 95% interval 128–140. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.50cache read $0.55$27.50cache write $6.875Not published by the provider
64.6
Good value (64.6). Cheaper per task than its benchmark results predict. Plenty of data behind it.
61 ±9
Chatty (61 ±9). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
164.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
apac.anthropic.claude-opus-5 · apac
143.9
From 389 benchmarks. Plenty of data behind it.
134 ±6
Coding IQ 133.8, 95% interval 128–140. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.50cache read $0.55batch $2.75$27.50cache write $6.875batch $13.751M
64.6
Good value (64.6). Cheaper per task than its benchmark results predict. Plenty of data behind it.
61 ±9
Chatty (61 ±9). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
164.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
au.anthropic.claude-opus-5 · 🇦🇺 au
143.9
From 389 benchmarks. Plenty of data behind it.
134 ±6
Coding IQ 133.8, 95% interval 128–140. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.50cache read $0.55batch $2.75$27.50cache write $6.875batch $13.751M
64.6
Good value (64.6). Cheaper per task than its benchmark results predict. Plenty of data behind it.
61 ±9
Chatty (61 ±9). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
164.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
eu.anthropic.claude-opus-5 · 🇪🇺 eu
143.9
From 389 benchmarks. Plenty of data behind it.
134 ±6
Coding IQ 133.8, 95% interval 128–140. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.50cache read $0.55batch $2.75$27.50cache write $6.875batch $13.751M
64.6
Good value (64.6). Cheaper per task than its benchmark results predict. Plenty of data behind it.
61 ±9
Chatty (61 ±9). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
164.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
jp.anthropic.claude-opus-5 · 🇯🇵 jp
143.9
From 389 benchmarks. Plenty of data behind it.
134 ±6
Coding IQ 133.8, 95% interval 128–140. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.50cache read $0.55batch $2.75$27.50cache write $6.875batch $13.751M
64.6
Good value (64.6). Cheaper per task than its benchmark results predict. Plenty of data behind it.
61 ±9
Chatty (61 ±9). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
164.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
us-gov.anthropic.claude-opus-5 · 🇺🇸 us-gov
143.9
From 389 benchmarks. Plenty of data behind it.
134 ±6
Coding IQ 133.8, 95% interval 128–140. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$6.00cache read $0.60batch $3.00$30.00cache write $7.50batch $15.001M
64.6
Good value (64.6). Cheaper per task than its benchmark results predict. Plenty of data behind it.
61 ±9
Chatty (61 ±9). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
164.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
us.anthropic.claude-opus-5 · 🇺🇸 us
143.9
From 389 benchmarks. Plenty of data behind it.
134 ±6
Coding IQ 133.8, 95% interval 128–140. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.50cache read $0.55batch $2.75$27.50cache write $6.875batch $13.751M
64.6
Good value (64.6). Cheaper per task than its benchmark results predict. Plenty of data behind it.
61 ±9
Chatty (61 ±9). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
164.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
eu.anthropic.claude-opus-5-v1 · 🇪🇺 eu
143.9
From 389 benchmarks. Plenty of data behind it.
134 ±6
Coding IQ 133.8, 95% interval 128–140. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.50$27.50Not published by the provider
64.6
Good value (64.6). Cheaper per task than its benchmark results predict. Plenty of data behind it.
61 ±9
Chatty (61 ±9). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
164.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
global.anthropic.claude-opus-5-v1 · global
143.9
From 389 benchmarks. Plenty of data behind it.
134 ±6
Coding IQ 133.8, 95% interval 128–140. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.00$25.00Not published by the provider
64.6
Good value (64.6). Cheaper per task than its benchmark results predict. Plenty of data behind it.
61 ±9
Chatty (61 ±9). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
164.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
us.anthropic.claude-opus-5-v1 · 🇺🇸 us
143.9
From 389 benchmarks. Plenty of data behind it.
134 ±6
Coding IQ 133.8, 95% interval 128–140. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.50$27.50Not published by the provider
64.6
Good value (64.6). Cheaper per task than its benchmark results predict. Plenty of data behind it.
61 ±9
Chatty (61 ±9). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
164.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
anthropic.claude-opus-5-v1
143.9
From 389 benchmarks. Plenty of data behind it.
134 ±6
Coding IQ 133.8, 95% interval 128–140. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.00$25.00Not published by the provider
64.6
Good value (64.6). Cheaper per task than its benchmark results predict. Plenty of data behind it.
61 ±9
Chatty (61 ±9). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
164.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 5.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
anthropic.claude-sonnet-5-5
143.9
From 270 benchmarks. Plenty of data behind it.
140 ±5
Coding IQ 140.0, 95% interval 135–145. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.10$10.00cache write $2.501M
66.7
Good value (66.7). Cheaper per task than its benchmark results predict. Plenty of data behind it.
38 ±9
Terse (38 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
166.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 5.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
apac.anthropic.claude-sonnet-5-5 · apac
143.9
From 270 benchmarks. Plenty of data behind it.
140 ±5
Coding IQ 140.0, 95% interval 135–145. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.20cache read $0.11$11.00cache write $2.751M
66.7
Good value (66.7). Cheaper per task than its benchmark results predict. Plenty of data behind it.
38 ±9
Terse (38 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
166.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 5.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
au.anthropic.claude-sonnet-5-5 · 🇦🇺 au
143.9
From 270 benchmarks. Plenty of data behind it.
140 ±5
Coding IQ 140.0, 95% interval 135–145. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.20cache read $0.11$11.00cache write $2.751M
66.7
Good value (66.7). Cheaper per task than its benchmark results predict. Plenty of data behind it.
38 ±9
Terse (38 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
166.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 5.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
ca.anthropic.claude-sonnet-5-5 · 🇨🇦 ca
143.9
From 270 benchmarks. Plenty of data behind it.
140 ±5
Coding IQ 140.0, 95% interval 135–145. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.20cache read $0.11$11.00cache write $2.751M
66.7
Good value (66.7). Cheaper per task than its benchmark results predict. Plenty of data behind it.
38 ±9
Terse (38 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
166.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 5.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
eu.anthropic.claude-sonnet-5-5 · 🇪🇺 eu
143.9
From 270 benchmarks. Plenty of data behind it.
140 ±5
Coding IQ 140.0, 95% interval 135–145. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.20cache read $0.11$11.00cache write $2.751M
66.7
Good value (66.7). Cheaper per task than its benchmark results predict. Plenty of data behind it.
38 ±9
Terse (38 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
166.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 5.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
global.anthropic.claude-sonnet-5-5 · global
143.9
From 270 benchmarks. Plenty of data behind it.
140 ±5
Coding IQ 140.0, 95% interval 135–145. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.10$10.00cache write $2.501M
66.7
Good value (66.7). Cheaper per task than its benchmark results predict. Plenty of data behind it.
38 ±9
Terse (38 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
166.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 5.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
jp.anthropic.claude-sonnet-5-5 · 🇯🇵 jp
143.9
From 270 benchmarks. Plenty of data behind it.
140 ±5
Coding IQ 140.0, 95% interval 135–145. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.20cache read $0.11$11.00cache write $2.751M
66.7
Good value (66.7). Cheaper per task than its benchmark results predict. Plenty of data behind it.
38 ±9
Terse (38 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
166.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 5.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
us-gov.anthropic.claude-sonnet-5-5 · 🇺🇸 us-gov
143.9
From 270 benchmarks. Plenty of data behind it.
140 ±5
Coding IQ 140.0, 95% interval 135–145. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.40cache read $0.12$12.00cache write $3.001M
66.7
Good value (66.7). Cheaper per task than its benchmark results predict. Plenty of data behind it.
38 ±9
Terse (38 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
166.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 5.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
us.anthropic.claude-sonnet-5-5 · 🇺🇸 us
143.9
From 270 benchmarks. Plenty of data behind it.
140 ±5
Coding IQ 140.0, 95% interval 135–145. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.20cache read $0.11$11.00cache write $2.751M
66.7
Good value (66.7). Cheaper per task than its benchmark results predict. Plenty of data behind it.
38 ±9
Terse (38 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
166.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 5.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
eu.anthropic.claude-sonnet-5-5-v1 · 🇪🇺 eu
143.9
From 270 benchmarks. Plenty of data behind it.
140 ±5
Coding IQ 140.0, 95% interval 135–145. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.20$11.00Not published by the provider
66.7
Good value (66.7). Cheaper per task than its benchmark results predict. Plenty of data behind it.
38 ±9
Terse (38 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
166.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 5.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
global.anthropic.claude-sonnet-5-5-v1 · global
143.9
From 270 benchmarks. Plenty of data behind it.
140 ±5
Coding IQ 140.0, 95% interval 135–145. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00$10.00Not published by the provider
66.7
Good value (66.7). Cheaper per task than its benchmark results predict. Plenty of data behind it.
38 ±9
Terse (38 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
166.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 5.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
us.anthropic.claude-sonnet-5-5-v1 · 🇺🇸 us
143.9
From 270 benchmarks. Plenty of data behind it.
140 ±5
Coding IQ 140.0, 95% interval 135–145. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.20$11.00Not published by the provider
66.7
Good value (66.7). Cheaper per task than its benchmark results predict. Plenty of data behind it.
38 ±9
Terse (38 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
166.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 5.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
anthropic.claude-sonnet-5-5-v1
143.9
From 270 benchmarks. Plenty of data behind it.
140 ±5
Coding IQ 140.0, 95% interval 135–145. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00$10.00Not published by the provider
66.7
Good value (66.7). Cheaper per task than its benchmark results predict. Plenty of data behind it.
38 ±9
Terse (38 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
166.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Fable 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Fable 5.2We compared release dates and version names in our catalogue.
anthropic.claude-fable-5
143.0
From 383 benchmarks. Plenty of data behind it.
132 ±5
Coding IQ 132.1, 95% interval 128–137. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$10.00cache read $1.00$50.00cache write $12.501M
57.1
Good value (57.1). Cheaper per task than its benchmark results predict. Plenty of data behind it.
53 ±10
Typical (53 ±10). Generates about as many tokens as models with similar coding results. Measured at default effort. A fair amount of data behind it.
164.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Fable 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Fable 5.2We compared release dates and version names in our catalogue.
global.anthropic.claude-fable-5-v1:0 · global
143.0
From 383 benchmarks. Plenty of data behind it.
132 ±5
Coding IQ 132.1, 95% interval 128–137. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$10.00cache read $1.00$50.00cache write $12.50Not published by the provider
57.1
Good value (57.1). Cheaper per task than its benchmark results predict. Plenty of data behind it.
53 ±10
Typical (53 ±10). Generates about as many tokens as models with similar coding results. Measured at default effort. A fair amount of data behind it.
164.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Fable 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Fable 5.2We compared release dates and version names in our catalogue.
regional.anthropic.claude-fable-5-v1:0 · regional
143.0
From 383 benchmarks. Plenty of data behind it.
132 ±5
Coding IQ 132.1, 95% interval 128–137. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$11.00cache read $1.10$55.00cache write $13.75Not published by the provider
57.1
Good value (57.1). Cheaper per task than its benchmark results predict. Plenty of data behind it.
53 ±10
Typical (53 ±10). Generates about as many tokens as models with similar coding results. Measured at default effort. A fair amount of data behind it.
164.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Fable 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Fable 5.2We compared release dates and version names in our catalogue.
apac.anthropic.claude-fable-5 · apac
143.0
From 383 benchmarks. Plenty of data behind it.
132 ±5
Coding IQ 132.1, 95% interval 128–137. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$11.00cache read $1.10$55.00cache write $13.751M
57.1
Good value (57.1). Cheaper per task than its benchmark results predict. Plenty of data behind it.
53 ±10
Typical (53 ±10). Generates about as many tokens as models with similar coding results. Measured at default effort. A fair amount of data behind it.
164.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Fable 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Fable 5.2We compared release dates and version names in our catalogue.
au.anthropic.claude-fable-5 · 🇦🇺 au
143.0
From 383 benchmarks. Plenty of data behind it.
132 ±5
Coding IQ 132.1, 95% interval 128–137. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$11.00cache read $1.10$55.00cache write $13.751M
57.1
Good value (57.1). Cheaper per task than its benchmark results predict. Plenty of data behind it.
53 ±10
Typical (53 ±10). Generates about as many tokens as models with similar coding results. Measured at default effort. A fair amount of data behind it.
164.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Fable 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Fable 5.2We compared release dates and version names in our catalogue.
eu.anthropic.claude-fable-5 · 🇪🇺 eu
143.0
From 383 benchmarks. Plenty of data behind it.
132 ±5
Coding IQ 132.1, 95% interval 128–137. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$11.00cache read $1.10$55.00cache write $13.751M
57.1
Good value (57.1). Cheaper per task than its benchmark results predict. Plenty of data behind it.
53 ±10
Typical (53 ±10). Generates about as many tokens as models with similar coding results. Measured at default effort. A fair amount of data behind it.
164.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Fable 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Fable 5.2We compared release dates and version names in our catalogue.
global.anthropic.claude-fable-5 · global
143.0
From 383 benchmarks. Plenty of data behind it.
132 ±5
Coding IQ 132.1, 95% interval 128–137. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$10.00cache read $1.00$50.00cache write $12.501M
57.1
Good value (57.1). Cheaper per task than its benchmark results predict. Plenty of data behind it.
53 ±10
Typical (53 ±10). Generates about as many tokens as models with similar coding results. Measured at default effort. A fair amount of data behind it.
164.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Fable 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Fable 5.2We compared release dates and version names in our catalogue.
us.anthropic.claude-fable-5 · 🇺🇸 us
143.0
From 383 benchmarks. Plenty of data behind it.
132 ±5
Coding IQ 132.1, 95% interval 128–137. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$11.00cache read $1.10$55.00cache write $13.751M
57.1
Good value (57.1). Cheaper per task than its benchmark results predict. Plenty of data behind it.
53 ±10
Typical (53 ±10). Generates about as many tokens as models with similar coding results. Measured at default effort. A fair amount of data behind it.
164.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Fable 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Fable 5.2We compared release dates and version names in our catalogue.
eu.anthropic.claude-fable-5-v1 · 🇪🇺 eu
143.0
From 383 benchmarks. Plenty of data behind it.
132 ±5
Coding IQ 132.1, 95% interval 128–137. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$11.00$55.00Not published by the provider
57.1
Good value (57.1). Cheaper per task than its benchmark results predict. Plenty of data behind it.
53 ±10
Typical (53 ±10). Generates about as many tokens as models with similar coding results. Measured at default effort. A fair amount of data behind it.
164.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Fable 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Fable 5.2We compared release dates and version names in our catalogue.
global.anthropic.claude-fable-5-v1 · global
143.0
From 383 benchmarks. Plenty of data behind it.
132 ±5
Coding IQ 132.1, 95% interval 128–137. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$10.00$50.00Not published by the provider
57.1
Good value (57.1). Cheaper per task than its benchmark results predict. Plenty of data behind it.
53 ±10
Typical (53 ±10). Generates about as many tokens as models with similar coding results. Measured at default effort. A fair amount of data behind it.
164.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Fable 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Fable 5.2We compared release dates and version names in our catalogue.
us.anthropic.claude-fable-5-v1 · 🇺🇸 us
143.0
From 383 benchmarks. Plenty of data behind it.
132 ±5
Coding IQ 132.1, 95% interval 128–137. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$11.00$55.00Not published by the provider
57.1
Good value (57.1). Cheaper per task than its benchmark results predict. Plenty of data behind it.
53 ±10
Typical (53 ±10). Generates about as many tokens as models with similar coding results. Measured at default effort. A fair amount of data behind it.
164.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Fable 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Fable 5.2We compared release dates and version names in our catalogue.
anthropic.claude-fable-5-v1
143.0
From 383 benchmarks. Plenty of data behind it.
132 ±5
Coding IQ 132.1, 95% interval 128–137. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$10.00$50.00Not published by the provider
57.1
Good value (57.1). Cheaper per task than its benchmark results predict. Plenty of data behind it.
53 ±10
Typical (53 ±10). Generates about as many tokens as models with similar coding results. Measured at default effort. A fair amount of data behind it.
164.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-6.1 Terra
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
openai.gpt-6.1-terra
142.5
From 130 benchmarks. Plenty of data behind it.
130 ±13
Coding IQ 130.4, 95% interval 118–143. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.10cache read $0.055$5.50cache write $1.375922K
54.7
Good value (54.7). Cheaper per task than its benchmark results predict. Plenty of data behind it.
52 ±9
Typical (52 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
167.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-6.1 Terra
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
global.openai.gpt-6.1-terra · global
142.5
From 130 benchmarks. Plenty of data behind it.
130 ±13
Coding IQ 130.4, 95% interval 118–143. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.00cache read $0.05$5.00cache write $1.25922K
54.7
Good value (54.7). Cheaper per task than its benchmark results predict. Plenty of data behind it.
52 ±9
Typical (52 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
167.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-6.1 Terra
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
us.openai.gpt-6.1-terra · 🇺🇸 us
142.5
From 130 benchmarks. Plenty of data behind it.
130 ±13
Coding IQ 130.4, 95% interval 118–143. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.10cache read $0.055$5.50cache write $1.375922K
54.7
Good value (54.7). Cheaper per task than its benchmark results predict. Plenty of data behind it.
52 ±9
Typical (52 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
167.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-6 Sol
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
openai.gpt-6-sol
142.5
From 210 benchmarks. Plenty of data behind it.
130 ±7
Coding IQ 129.5, 95% interval 123–136. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.20cache read $0.22$11.00cache write $2.75922K
63.4
Good value (63.4). Cheaper per task than its benchmark results predict. Plenty of data behind it.
48 ±9
Typical (48 ±9). Generates about as many tokens as models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate.
163.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-6 Sol
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
global.openai.gpt-6-sol · global
142.5
From 210 benchmarks. Plenty of data behind it.
130 ±7
Coding IQ 129.5, 95% interval 123–136. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.20$10.00cache write $2.50922K
63.4
Good value (63.4). Cheaper per task than its benchmark results predict. Plenty of data behind it.
48 ±9
Typical (48 ±9). Generates about as many tokens as models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate.
163.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-6 Sol
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
us.openai.gpt-6-sol · 🇺🇸 us
142.5
From 210 benchmarks. Plenty of data behind it.
130 ±7
Coding IQ 129.5, 95% interval 123–136. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.20cache read $0.22$11.00cache write $2.75922K
63.4
Good value (63.4). Cheaper per task than its benchmark results predict. Plenty of data behind it.
48 ±9
Typical (48 ±9). Generates about as many tokens as models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate.
163.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-5.6 Sol
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-6.2 SolWe compared release dates and version names in our catalogue.
openai.gpt-5.6-sol
141.6
From 504 benchmarks. Plenty of data behind it.
125 ±5
Coding IQ 125.1, 95% interval 120–130. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$4.40cache read $0.44$22.00cache write $5.50922K
59.9
Good value (59.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
41 ±8
Terse (41 ±8). Generates fewer tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
163
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-5.6 Sol
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-6.2 SolWe compared release dates and version names in our catalogue.
global.openai.gpt-5.6-sol · global
141.6
From 504 benchmarks. Plenty of data behind it.
125 ±5
Coding IQ 125.1, 95% interval 120–130. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$4.00cache read $0.40$20.00cache write $5.00922K
59.9
Good value (59.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
41 ±8
Terse (41 ±8). Generates fewer tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
163
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-5.6 Sol
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-6.2 SolWe compared release dates and version names in our catalogue.
us.openai.gpt-5.6-sol · 🇺🇸 us
141.6
From 504 benchmarks. Plenty of data behind it.
125 ±5
Coding IQ 125.1, 95% interval 120–130. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$4.40cache read $0.44$22.00cache write $5.50922K
59.9
Good value (59.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
41 ±8
Terse (41 ±8). Generates fewer tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
163
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 5.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT 6We compared the version names in our catalogue.
openai.gpt-5.5
139.8
From 476 benchmarks. Plenty of data behind it.
122 ±12
Coding IQ 121.5, 95% interval 110–134. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.50cache read $0.55$33.00922K
64.0
Good value (64.0). Cheaper per task than its benchmark results predict. Plenty of data behind it.
28 ±8
Terse (28 ±8). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
160.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 5.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT 6We compared the version names in our catalogue.
global.openai.gpt-5.5 · global
139.8
From 476 benchmarks. Plenty of data behind it.
122 ±12
Coding IQ 121.5, 95% interval 110–134. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.00cache read $0.50$30.00922K
64.0
Good value (64.0). Cheaper per task than its benchmark results predict. Plenty of data behind it.
28 ±8
Terse (28 ±8). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
160.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 5.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT 6We compared the version names in our catalogue.
us.openai.gpt-5.5 · 🇺🇸 us
139.8
From 476 benchmarks. Plenty of data behind it.
122 ±12
Coding IQ 121.5, 95% interval 110–134. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.50cache read $0.55$33.00922K
64.0
Good value (64.0). Cheaper per task than its benchmark results predict. Plenty of data behind it.
28 ±8
Terse (28 ±8). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
160.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.8
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
anthropic.claude-opus-4-8
139.7
From 478 benchmarks. Plenty of data behind it.
121 ±4
Coding IQ 120.8, 95% interval 116–125. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.00cache read $0.50$25.00cache write $6.251M
52.9
Good value (52.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
40 ±10
Terse (40 ±10). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
159.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.8
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
global.anthropic.claude-opus-4-8-v1:0 · global
139.7
From 478 benchmarks. Plenty of data behind it.
121 ±4
Coding IQ 120.8, 95% interval 116–125. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.00cache read $0.50$25.00cache write $6.25Not published by the provider
52.9
Good value (52.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
40 ±10
Terse (40 ±10). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
159.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.8
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
regional.anthropic.claude-opus-4-8-v1:0 · regional
139.7
From 478 benchmarks. Plenty of data behind it.
121 ±4
Coding IQ 120.8, 95% interval 116–125. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.50cache read $0.55$27.50cache write $6.875Not published by the provider
52.9
Good value (52.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
40 ±10
Terse (40 ±10). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
159.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.8
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
apac.anthropic.claude-opus-4-8 · apac
139.7
From 478 benchmarks. Plenty of data behind it.
121 ±4
Coding IQ 120.8, 95% interval 116–125. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.50cache read $0.55$27.50cache write $6.8751M
52.9
Good value (52.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
40 ±10
Terse (40 ±10). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
159.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.8
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
au.anthropic.claude-opus-4-8 · 🇦🇺 au
139.7
From 478 benchmarks. Plenty of data behind it.
121 ±4
Coding IQ 120.8, 95% interval 116–125. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.50cache read $0.55$27.50cache write $6.8751M
52.9
Good value (52.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
40 ±10
Terse (40 ±10). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
159.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.8
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
eu.anthropic.claude-opus-4-8 · 🇪🇺 eu
139.7
From 478 benchmarks. Plenty of data behind it.
121 ±4
Coding IQ 120.8, 95% interval 116–125. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.50cache read $0.55$27.50cache write $6.8751M
52.9
Good value (52.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
40 ±10
Terse (40 ±10). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
159.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.8
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
global.anthropic.claude-opus-4-8 · global
139.7
From 478 benchmarks. Plenty of data behind it.
121 ±4
Coding IQ 120.8, 95% interval 116–125. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.00cache read $0.50$25.00cache write $6.251M
52.9
Good value (52.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
40 ±10
Terse (40 ±10). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
159.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.8
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
jp.anthropic.claude-opus-4-8 · 🇯🇵 jp
139.7
From 478 benchmarks. Plenty of data behind it.
121 ±4
Coding IQ 120.8, 95% interval 116–125. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.50cache read $0.55$27.50cache write $6.8751M
52.9
Good value (52.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
40 ±10
Terse (40 ±10). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
159.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.8
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
us-gov.anthropic.claude-opus-4-8 · 🇺🇸 us-gov
139.7
From 478 benchmarks. Plenty of data behind it.
121 ±4
Coding IQ 120.8, 95% interval 116–125. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$6.00cache read $0.60$30.00cache write $7.501M
52.9
Good value (52.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
40 ±10
Terse (40 ±10). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
159.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.8
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
us.anthropic.claude-opus-4-8 · 🇺🇸 us
139.7
From 478 benchmarks. Plenty of data behind it.
121 ±4
Coding IQ 120.8, 95% interval 116–125. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.50cache read $0.55$27.50cache write $6.8751M
52.9
Good value (52.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
40 ±10
Terse (40 ±10). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
159.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.8
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
eu.anthropic.claude-opus-4-8-v1 · 🇪🇺 eu
139.7
From 478 benchmarks. Plenty of data behind it.
121 ±4
Coding IQ 120.8, 95% interval 116–125. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.50$27.50Not published by the provider
52.9
Good value (52.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
40 ±10
Terse (40 ±10). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
159.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.8
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
global.anthropic.claude-opus-4-8-v1 · global
139.7
From 478 benchmarks. Plenty of data behind it.
121 ±4
Coding IQ 120.8, 95% interval 116–125. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.00$25.00Not published by the provider
52.9
Good value (52.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
40 ±10
Terse (40 ±10). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
159.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.8
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
us.anthropic.claude-opus-4-8-v1 · 🇺🇸 us
139.7
From 478 benchmarks. Plenty of data behind it.
121 ±4
Coding IQ 120.8, 95% interval 116–125. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.50$27.50Not published by the provider
52.9
Good value (52.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
40 ±10
Terse (40 ±10). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
159.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.8
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
anthropic.claude-opus-4-8-v1
139.7
From 478 benchmarks. Plenty of data behind it.
121 ±4
Coding IQ 120.8, 95% interval 116–125. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.00$25.00Not published by the provider
52.9
Good value (52.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
40 ±10
Terse (40 ±10). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
159.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Kimi K3
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Newer version
Newer versionKimi K3.1We compared the version names in our catalogue.
moonshotai.kimi-k3
139.2
From 417 benchmarks. Plenty of data behind it.
124 ±7
Coding IQ 123.8, 95% interval 117–131. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.96cache read $0.396batch $1.98$19.80cache write $4.95batch $9.90869K
60.2
Good value (60.2). Cheaper per task than its benchmark results predict. Plenty of data behind it.
55 ±9
Typical (55 ±9). Generates about as many tokens as models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate.
158.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Kimi K3
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Newer version
Newer versionKimi K3.1We compared the version names in our catalogue.
global.moonshotai.kimi-k3 · global
139.2
From 417 benchmarks. Plenty of data behind it.
124 ±7
Coding IQ 123.8, 95% interval 117–131. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.00cache read $0.30$15.00cache write $3.751M
60.2
Good value (60.2). Cheaper per task than its benchmark results predict. Plenty of data behind it.
55 ±9
Typical (55 ±9). Generates about as many tokens as models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate.
158.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Kimi K3
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Newer version
Newer versionKimi K3.1We compared the version names in our catalogue.
us.moonshotai.kimi-k3 · 🇺🇸 us
139.2
From 417 benchmarks. Plenty of data behind it.
124 ±7
Coding IQ 123.8, 95% interval 117–131. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.30cache read $0.33$16.50cache write $4.1251M
60.2
Good value (60.2). Cheaper per task than its benchmark results predict. Plenty of data behind it.
55 ±9
Typical (55 ±9). Generates about as many tokens as models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate.
158.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.7
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
anthropic.claude-opus-4-7
138.2
From 354 benchmarks. Plenty of data behind it.
118 ±15
Coding IQ 118.2, 95% interval 103–134. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.00cache read $0.50$25.00cache write $6.251M
49.6
Fair value (49.6). Costs per task about what its benchmark results predict. Plenty of data behind it.
38 ±12
Terse (38 ±12). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
157.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.7
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
global.anthropic.claude-opus-4-7-v1:0 · global
138.2
From 354 benchmarks. Plenty of data behind it.
118 ±15
Coding IQ 118.2, 95% interval 103–134. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.00cache read $0.50$25.00cache write $6.25Not published by the provider
49.6
Fair value (49.6). Costs per task about what its benchmark results predict. Plenty of data behind it.
38 ±12
Terse (38 ±12). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
157.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.7
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
regional.anthropic.claude-opus-4-7-v1:0 · regional
138.2
From 354 benchmarks. Plenty of data behind it.
118 ±15
Coding IQ 118.2, 95% interval 103–134. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.50cache read $0.55$27.50cache write $6.875Not published by the provider
49.6
Fair value (49.6). Costs per task about what its benchmark results predict. Plenty of data behind it.
38 ±12
Terse (38 ±12). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
157.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.7
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
apac.anthropic.claude-opus-4-7 · apac
138.2
From 354 benchmarks. Plenty of data behind it.
118 ±15
Coding IQ 118.2, 95% interval 103–134. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.50cache read $0.55$27.50cache write $6.8751M
49.6
Fair value (49.6). Costs per task about what its benchmark results predict. Plenty of data behind it.
38 ±12
Terse (38 ±12). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
157.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.7
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
au.anthropic.claude-opus-4-7 · 🇦🇺 au
138.2
From 354 benchmarks. Plenty of data behind it.
118 ±15
Coding IQ 118.2, 95% interval 103–134. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.50cache read $0.55$27.50cache write $6.8751M
49.6
Fair value (49.6). Costs per task about what its benchmark results predict. Plenty of data behind it.
38 ±12
Terse (38 ±12). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
157.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.7
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
eu.anthropic.claude-opus-4-7 · 🇪🇺 eu
138.2
From 354 benchmarks. Plenty of data behind it.
118 ±15
Coding IQ 118.2, 95% interval 103–134. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.50cache read $0.55$27.50cache write $6.8751M
49.6
Fair value (49.6). Costs per task about what its benchmark results predict. Plenty of data behind it.
38 ±12
Terse (38 ±12). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
157.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.7
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
global.anthropic.claude-opus-4-7 · global
138.2
From 354 benchmarks. Plenty of data behind it.
118 ±15
Coding IQ 118.2, 95% interval 103–134. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.00cache read $0.50$25.00cache write $6.251M
49.6
Fair value (49.6). Costs per task about what its benchmark results predict. Plenty of data behind it.
38 ±12
Terse (38 ±12). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
157.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.7
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
jp.anthropic.claude-opus-4-7 · 🇯🇵 jp
138.2
From 354 benchmarks. Plenty of data behind it.
118 ±15
Coding IQ 118.2, 95% interval 103–134. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.50cache read $0.55$27.50cache write $6.8751M
49.6
Fair value (49.6). Costs per task about what its benchmark results predict. Plenty of data behind it.
38 ±12
Terse (38 ±12). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
157.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.7
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
us.anthropic.claude-opus-4-7 · 🇺🇸 us
138.2
From 354 benchmarks. Plenty of data behind it.
118 ±15
Coding IQ 118.2, 95% interval 103–134. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.50cache read $0.55$27.50cache write $6.8751M
49.6
Fair value (49.6). Costs per task about what its benchmark results predict. Plenty of data behind it.
38 ±12
Terse (38 ±12). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
157.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.7
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
eu.anthropic.claude-opus-4-7-v1 · 🇪🇺 eu
138.2
From 354 benchmarks. Plenty of data behind it.
118 ±15
Coding IQ 118.2, 95% interval 103–134. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.50$27.50Not published by the provider
49.6
Fair value (49.6). Costs per task about what its benchmark results predict. Plenty of data behind it.
38 ±12
Terse (38 ±12). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
157.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.7
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
global.anthropic.claude-opus-4-7-v1 · global
138.2
From 354 benchmarks. Plenty of data behind it.
118 ±15
Coding IQ 118.2, 95% interval 103–134. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.00$25.00Not published by the provider
49.6
Fair value (49.6). Costs per task about what its benchmark results predict. Plenty of data behind it.
38 ±12
Terse (38 ±12). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
157.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.7
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
us.anthropic.claude-opus-4-7-v1 · 🇺🇸 us
138.2
From 354 benchmarks. Plenty of data behind it.
118 ±15
Coding IQ 118.2, 95% interval 103–134. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.50$27.50Not published by the provider
49.6
Fair value (49.6). Costs per task about what its benchmark results predict. Plenty of data behind it.
38 ±12
Terse (38 ±12). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
157.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.7
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
anthropic.claude-opus-4-7-v1
138.2
From 354 benchmarks. Plenty of data behind it.
118 ±15
Coding IQ 118.2, 95% interval 103–134. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.00$25.00Not published by the provider
49.6
Fair value (49.6). Costs per task about what its benchmark results predict. Plenty of data behind it.
38 ±12
Terse (38 ±12). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
157.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
zai.glm-5.3
138.2
From 318 benchmarks. Plenty of data behind it.
121 ±9
Coding IQ 121.0, 95% interval 112–130. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.68$5.28Not published by the provider
57.7
Good value (57.7). Cheaper per task than its benchmark results predict. Plenty of data behind it.
65 ±10
Chatty (65 ±10). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
157.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
global.zai.glm-5.3 · global
138.2
From 318 benchmarks. Plenty of data behind it.
121 ±9
Coding IQ 121.0, 95% interval 112–130. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.68cache read $0.312batch $0.84$5.28cache write $2.10batch $2.641M
57.7
Good value (57.7). Cheaper per task than its benchmark results predict. Plenty of data behind it.
65 ±10
Chatty (65 ±10). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
157.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
us.zai.glm-5.3 · 🇺🇸 us
138.2
From 318 benchmarks. Plenty of data behind it.
121 ±9
Coding IQ 121.0, 95% interval 112–130. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.848cache read $0.3432batch $0.924$5.808cache write $2.31batch $2.9041M
57.7
Good value (57.7). Cheaper per task than its benchmark results predict. Plenty of data behind it.
65 ±10
Chatty (65 ±10). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
157.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.6
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
xai.grok-4.6
138.0
From 220 benchmarks. Plenty of data behind it.
120 ±11
Coding IQ 120.1, 95% interval 109–131. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.64cache read $0.66$7.92500K
56.0
Good value (56.0). Cheaper per task than its benchmark results predict. Plenty of data behind it.
47 ±10
Typical (47 ±10). Generates about as many tokens as models with similar coding results. Measured at high effort. A fair amount of data behind it.
157.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.6
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
global.xai.grok-4.6 · global
138.0
From 220 benchmarks. Plenty of data behind it.
120 ±11
Coding IQ 120.1, 95% interval 109–131. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.50$6.00500K
56.0
Good value (56.0). Cheaper per task than its benchmark results predict. Plenty of data behind it.
47 ±10
Typical (47 ±10). Generates about as many tokens as models with similar coding results. Measured at high effort. A fair amount of data behind it.
157.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.6
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
us-gov.xai.grok-4.6 · 🇺🇸 us-gov
138.0
From 220 benchmarks. Plenty of data behind it.
120 ±11
Coding IQ 120.1, 95% interval 109–131. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.64cache read $0.66$7.92500K
56.0
Good value (56.0). Cheaper per task than its benchmark results predict. Plenty of data behind it.
47 ±10
Typical (47 ±10). Generates about as many tokens as models with similar coding results. Measured at high effort. A fair amount of data behind it.
157.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.6
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
us.xai.grok-4.6 · 🇺🇸 us
138.0
From 220 benchmarks. Plenty of data behind it.
120 ±11
Coding IQ 120.1, 95% interval 109–131. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.20cache read $0.55$6.60500K
56.0
Good value (56.0). Cheaper per task than its benchmark results predict. Plenty of data behind it.
47 ±10
Typical (47 ±10). Generates about as many tokens as models with similar coding results. Measured at high effort. A fair amount of data behind it.
157.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.7
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
xai.grok-4.7
137.7
From 249 benchmarks. Plenty of data behind it.
117 ±7
Coding IQ 117.4, 95% interval 111–124. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.64cache read $0.66batch $1.32$7.92batch $3.96524K
41.2
Poor value (41.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
55 ±14
Typical (55 ±14). Generates about as many tokens as models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate.
156.4
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.7
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
global.xai.grok-4.7 · global
137.7
From 249 benchmarks. Plenty of data behind it.
117 ±7
Coding IQ 117.4, 95% interval 111–124. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.50$6.00524K
41.2
Poor value (41.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
55 ±14
Typical (55 ±14). Generates about as many tokens as models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate.
156.4
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.7
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
us-gov.xai.grok-4.7 · 🇺🇸 us-gov
137.7
From 249 benchmarks. Plenty of data behind it.
117 ±7
Coding IQ 117.4, 95% interval 111–124. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.64cache read $0.66batch $1.32$7.92batch $3.96524K
41.2
Poor value (41.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
55 ±14
Typical (55 ±14). Generates about as many tokens as models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate.
156.4
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.7
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
us.xai.grok-4.7 · 🇺🇸 us
137.7
From 249 benchmarks. Plenty of data behind it.
117 ±7
Coding IQ 117.4, 95% interval 111–124. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.20cache read $0.55$6.60524K
41.2
Poor value (41.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
55 ±14
Typical (55 ±14). Generates about as many tokens as models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate.
156.4
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.6
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
anthropic.claude-opus-4-6-v1
136.9
From 466 benchmarks. Plenty of data behind it.
118 ±5
Coding IQ 117.9, 95% interval 113–123. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.00cache read $0.50$25.00cache write $6.251M
47.2
Poor value (47.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
41 ±15
Terse (41 ±15). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
156.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.6
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
global.anthropic.claude-opus-4-6-v1:0 · global
136.9
From 466 benchmarks. Plenty of data behind it.
118 ±5
Coding IQ 117.9, 95% interval 113–123. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.00cache read $0.50$25.00cache write $6.25Not published by the provider
47.2
Poor value (47.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
41 ±15
Terse (41 ±15). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
156.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.6
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
regional.anthropic.claude-opus-4-6-v1:0 · regional
136.9
From 466 benchmarks. Plenty of data behind it.
118 ±5
Coding IQ 117.9, 95% interval 113–123. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.50cache read $0.55$27.50cache write $6.875Not published by the provider
47.2
Poor value (47.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
41 ±15
Terse (41 ±15). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
156.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.6
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
au.anthropic.claude-opus-4-6-v1 · 🇦🇺 au
136.9
From 466 benchmarks. Plenty of data behind it.
118 ±5
Coding IQ 117.9, 95% interval 113–123. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.50cache read $0.55$27.50cache write $6.8751M
47.2
Poor value (47.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
41 ±15
Terse (41 ±15). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
156.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.6
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
eu.anthropic.claude-opus-4-6-v1 · 🇪🇺 eu
136.9
From 466 benchmarks. Plenty of data behind it.
118 ±5
Coding IQ 117.9, 95% interval 113–123. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.50cache read $0.55$27.50cache write $6.8751M
47.2
Poor value (47.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
41 ±15
Terse (41 ±15). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
156.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.6
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
global.anthropic.claude-opus-4-6-v1 · global
136.9
From 466 benchmarks. Plenty of data behind it.
118 ±5
Coding IQ 117.9, 95% interval 113–123. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.00cache read $0.50$25.00cache write $6.251M
47.2
Poor value (47.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
41 ±15
Terse (41 ±15). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
156.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.6
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
us.anthropic.claude-opus-4-6-v1 · 🇺🇸 us
136.9
From 466 benchmarks. Plenty of data behind it.
118 ±5
Coding IQ 117.9, 95% interval 113–123. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.50cache read $0.55$27.50cache write $6.8751M
47.2
Poor value (47.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
41 ±15
Terse (41 ±15). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
156.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.6
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
136.9
From 466 benchmarks. Plenty of data behind it.
118 ±5
Coding IQ 117.9, 95% interval 113–123. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.00$25.00Not published by the provider
47.2
Poor value (47.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
41 ±15
Terse (41 ±15). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
156.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.6
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
eu.anthropic.claude-opus-4-6-v1:0 · 🇪🇺 eu
136.9
From 466 benchmarks. Plenty of data behind it.
118 ±5
Coding IQ 117.9, 95% interval 113–123. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.50$27.50Not published by the provider
47.2
Poor value (47.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
41 ±15
Terse (41 ±15). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
156.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.6
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
us.anthropic.claude-opus-4-6-v1:0 · 🇺🇸 us
136.9
From 466 benchmarks. Plenty of data behind it.
118 ±5
Coding IQ 117.9, 95% interval 113–123. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.50$27.50Not published by the provider
47.2
Poor value (47.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
41 ±15
Terse (41 ±15). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
156.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.6
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
anthropic.claude-opus-4-6-v1:0
136.9
From 466 benchmarks. Plenty of data behind it.
118 ±5
Coding IQ 117.9, 95% interval 113–123. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.00$25.00Not published by the provider
47.2
Poor value (47.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
41 ±15
Terse (41 ±15). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
156.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 5.4
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT 6We compared the version names in our catalogue.
openai.gpt-5.4
136.8
From 489 benchmarks. Plenty of data behind it.
112 ±8
Coding IQ 112.0, 95% interval 104–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.75cache read $0.275$16.50922K
60.1
Good value (60.1). Cheaper per task than its benchmark results predict. Plenty of data behind it.
28 ±8
Terse (28 ±8). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
157.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 5.4
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT 6We compared the version names in our catalogue.
global.openai.gpt-5.4 · global
136.8
From 489 benchmarks. Plenty of data behind it.
112 ±8
Coding IQ 112.0, 95% interval 104–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.50cache read $0.25$15.00922K
60.1
Good value (60.1). Cheaper per task than its benchmark results predict. Plenty of data behind it.
28 ±8
Terse (28 ±8). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
157.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 5.4
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT 6We compared the version names in our catalogue.
us-gov.openai.gpt-5.4 · 🇺🇸 us-gov
136.8
From 489 benchmarks. Plenty of data behind it.
112 ±8
Coding IQ 112.0, 95% interval 104–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.30cache read $0.33$19.80922K
60.1
Good value (60.1). Cheaper per task than its benchmark results predict. Plenty of data behind it.
28 ±8
Terse (28 ±8). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
157.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 5.4
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT 6We compared the version names in our catalogue.
us.openai.gpt-5.4 · 🇺🇸 us
136.8
From 489 benchmarks. Plenty of data behind it.
112 ±8
Coding IQ 112.0, 95% interval 104–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.75cache read $0.275$16.50922K
60.1
Good value (60.1). Cheaper per task than its benchmark results predict. Plenty of data behind it.
28 ±8
Terse (28 ±8). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
157.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Sonnet 5.5We compared release dates and version names in our catalogue.
anthropic.claude-sonnet-5
136.3
From 360 benchmarks. Plenty of data behind it.
115 ±5
Coding IQ 115.2, 95% interval 111–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.20$10.00cache write $2.501M
37.4
Poor value (37.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
57 ±9
Chatty (57 ±9). Generates more tokens than models with similar coding results. Measured at medium effort. Little data behind it, so treat it as a rough estimate.
156.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Sonnet 5.5We compared release dates and version names in our catalogue.
global.anthropic.claude-sonnet-5-v1:0 · global
136.3
From 360 benchmarks. Plenty of data behind it.
115 ±5
Coding IQ 115.2, 95% interval 111–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
——Not published by the provider
37.4
Poor value (37.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
57 ±9
Chatty (57 ±9). Generates more tokens than models with similar coding results. Measured at medium effort. Little data behind it, so treat it as a rough estimate.
156.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Sonnet 5.5We compared release dates and version names in our catalogue.
regional.anthropic.claude-sonnet-5-v1:0 · regional
136.3
From 360 benchmarks. Plenty of data behind it.
115 ±5
Coding IQ 115.2, 95% interval 111–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
——Not published by the provider
37.4
Poor value (37.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
57 ±9
Chatty (57 ±9). Generates more tokens than models with similar coding results. Measured at medium effort. Little data behind it, so treat it as a rough estimate.
156.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Sonnet 5.5We compared release dates and version names in our catalogue.
apac.anthropic.claude-sonnet-5 · apac
136.3
From 360 benchmarks. Plenty of data behind it.
115 ±5
Coding IQ 115.2, 95% interval 111–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.20cache read $0.22$11.00cache write $2.751M
37.4
Poor value (37.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
57 ±9
Chatty (57 ±9). Generates more tokens than models with similar coding results. Measured at medium effort. Little data behind it, so treat it as a rough estimate.
156.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Sonnet 5.5We compared release dates and version names in our catalogue.
au.anthropic.claude-sonnet-5 · 🇦🇺 au
136.3
From 360 benchmarks. Plenty of data behind it.
115 ±5
Coding IQ 115.2, 95% interval 111–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.20cache read $0.22$11.00cache write $2.751M
37.4
Poor value (37.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
57 ±9
Chatty (57 ±9). Generates more tokens than models with similar coding results. Measured at medium effort. Little data behind it, so treat it as a rough estimate.
156.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Sonnet 5.5We compared release dates and version names in our catalogue.
eu.anthropic.claude-sonnet-5 · 🇪🇺 eu
136.3
From 360 benchmarks. Plenty of data behind it.
115 ±5
Coding IQ 115.2, 95% interval 111–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.20cache read $0.22$11.00cache write $2.751M
37.4
Poor value (37.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
57 ±9
Chatty (57 ±9). Generates more tokens than models with similar coding results. Measured at medium effort. Little data behind it, so treat it as a rough estimate.
156.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Sonnet 5.5We compared release dates and version names in our catalogue.
global.anthropic.claude-sonnet-5 · global
136.3
From 360 benchmarks. Plenty of data behind it.
115 ±5
Coding IQ 115.2, 95% interval 111–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.20$10.00cache write $2.501M
37.4
Poor value (37.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
57 ±9
Chatty (57 ±9). Generates more tokens than models with similar coding results. Measured at medium effort. Little data behind it, so treat it as a rough estimate.
156.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Sonnet 5.5We compared release dates and version names in our catalogue.
jp.anthropic.claude-sonnet-5 · 🇯🇵 jp
136.3
From 360 benchmarks. Plenty of data behind it.
115 ±5
Coding IQ 115.2, 95% interval 111–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.20cache read $0.22$11.00cache write $2.751M
37.4
Poor value (37.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
57 ±9
Chatty (57 ±9). Generates more tokens than models with similar coding results. Measured at medium effort. Little data behind it, so treat it as a rough estimate.
156.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Sonnet 5.5We compared release dates and version names in our catalogue.
us-gov.anthropic.claude-sonnet-5 · 🇺🇸 us-gov
136.3
From 360 benchmarks. Plenty of data behind it.
115 ±5
Coding IQ 115.2, 95% interval 111–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.40cache read $0.24$12.00cache write $3.001M
37.4
Poor value (37.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
57 ±9
Chatty (57 ±9). Generates more tokens than models with similar coding results. Measured at medium effort. Little data behind it, so treat it as a rough estimate.
156.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Sonnet 5.5We compared release dates and version names in our catalogue.
us.anthropic.claude-sonnet-5 · 🇺🇸 us
136.3
From 360 benchmarks. Plenty of data behind it.
115 ±5
Coding IQ 115.2, 95% interval 111–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.20cache read $0.22$11.00cache write $2.751M
37.4
Poor value (37.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
57 ±9
Chatty (57 ±9). Generates more tokens than models with similar coding results. Measured at medium effort. Little data behind it, so treat it as a rough estimate.
156.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Sonnet 5.5We compared release dates and version names in our catalogue.
eu.anthropic.claude-sonnet-5-v1 · 🇪🇺 eu
136.3
From 360 benchmarks. Plenty of data behind it.
115 ±5
Coding IQ 115.2, 95% interval 111–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.20$11.00Not published by the provider
37.4
Poor value (37.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
57 ±9
Chatty (57 ±9). Generates more tokens than models with similar coding results. Measured at medium effort. Little data behind it, so treat it as a rough estimate.
156.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Sonnet 5.5We compared release dates and version names in our catalogue.
global.anthropic.claude-sonnet-5-v1 · global
136.3
From 360 benchmarks. Plenty of data behind it.
115 ±5
Coding IQ 115.2, 95% interval 111–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00$10.00Not published by the provider
37.4
Poor value (37.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
57 ±9
Chatty (57 ±9). Generates more tokens than models with similar coding results. Measured at medium effort. Little data behind it, so treat it as a rough estimate.
156.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Sonnet 5.5We compared release dates and version names in our catalogue.
us.anthropic.claude-sonnet-5-v1 · 🇺🇸 us
136.3
From 360 benchmarks. Plenty of data behind it.
115 ±5
Coding IQ 115.2, 95% interval 111–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.20$11.00Not published by the provider
37.4
Poor value (37.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
57 ±9
Chatty (57 ±9). Generates more tokens than models with similar coding results. Measured at medium effort. Little data behind it, so treat it as a rough estimate.
156.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Sonnet 5.5We compared release dates and version names in our catalogue.
anthropic.claude-sonnet-5-v1
136.3
From 360 benchmarks. Plenty of data behind it.
115 ±5
Coding IQ 115.2, 95% interval 111–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00$10.00Not published by the provider
37.4
Poor value (37.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
57 ±9
Chatty (57 ±9). Generates more tokens than models with similar coding results. Measured at medium effort. Little data behind it, so treat it as a rough estimate.
156.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-5.6 Terra
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-6.1 TerraWe compared release dates and version names in our catalogue.
openai.gpt-5.6-terra
135.7
From 329 benchmarks. Plenty of data behind it.
121 ±5
Coding IQ 120.9, 95% interval 116–126. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.20cache read $0.22$13.20cache write $2.75922K
60.4
Good value (60.4). Cheaper per task than its benchmark results predict. Plenty of data behind it.
48 ±10
Typical (48 ±10). Generates about as many tokens as models with similar coding results. Measured at max effort. A fair amount of data behind it.
160.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-5.6 Terra
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-6.1 TerraWe compared release dates and version names in our catalogue.
global.openai.gpt-5.6-terra · global
135.7
From 329 benchmarks. Plenty of data behind it.
121 ±5
Coding IQ 120.9, 95% interval 116–126. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.20$12.00cache write $2.50922K
60.4
Good value (60.4). Cheaper per task than its benchmark results predict. Plenty of data behind it.
48 ±10
Typical (48 ±10). Generates about as many tokens as models with similar coding results. Measured at max effort. A fair amount of data behind it.
160.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-5.6 Terra
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-6.1 TerraWe compared release dates and version names in our catalogue.
us-gov.openai.gpt-5.6-terra · 🇺🇸 us-gov
135.7
From 329 benchmarks. Plenty of data behind it.
121 ±5
Coding IQ 120.9, 95% interval 116–126. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.64cache read $0.264$15.84cache write $3.30922K
60.4
Good value (60.4). Cheaper per task than its benchmark results predict. Plenty of data behind it.
48 ±10
Typical (48 ±10). Generates about as many tokens as models with similar coding results. Measured at max effort. A fair amount of data behind it.
160.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-5.6 Terra
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-6.1 TerraWe compared release dates and version names in our catalogue.
us.openai.gpt-5.6-terra · 🇺🇸 us
135.7
From 329 benchmarks. Plenty of data behind it.
121 ±5
Coding IQ 120.9, 95% interval 116–126. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.20cache read $0.22$13.20cache write $2.75922K
60.4
Good value (60.4). Cheaper per task than its benchmark results predict. Plenty of data behind it.
48 ±10
Typical (48 ±10). Generates about as many tokens as models with similar coding results. Measured at max effort. A fair amount of data behind it.
160.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API

Run by Amazon Web Services

73 listings on this page where Amazon Web Services runs the model. Another provider sells these listings.

Select a score for details.

About these columns
llminfo IQ
llminfo IQ (capability index). How llminfo IQ is computed
Coding IQ
llminfo Coding IQ (coding capability, its own scale). How Coding IQ is computed
Value
Value for money. 50 means as expected for its results. Above 50, cheaper per task. How Value for money works
Yap
Tokens used per coding task vs. models with the same results. Includes agents that write code. Chattiness on maths doesn't predict it. How the Yap score works
ModelProviderllminfo IQCoding IQInput $/1MOutput $/1MMax Input TokensValueYapEpoch Capabilities Index
Claude Fable 5.2
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
New
Released 9 Nov 2026
anthropic.claude-fable-5-2
 Llmgateway
149.0
From 171 benchmarks. Plenty of data behind it.
147 ±11
Coding IQ 146.6, 95% interval 135–158. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$8.00cache read $0.20$40.00cache write $10.00Not published by the provider
73.1
Good value (73.1). Cheaper per task than its benchmark results predict. Plenty of data behind it.
44 ±9
Terse (44 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
173.4
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-6.2 Astra
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
New
Released 17 Nov 2026
global
 OpenRouter
148.3
From 120 benchmarks. Plenty of data behind it.
142 ±9
Coding IQ 141.7, 95% interval 133–150. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$8.00cache read $0.40$40.00cache write $10.00922K
66.9
Good value (66.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
48 ±9
Typical (48 ±9). Generates about as many tokens as models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate.
172.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-6 Astra
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-6.2 AstraWe compared release dates and version names in our catalogue.
global
 OpenRouter
147.2
From 338 benchmarks. Plenty of data behind it.
139 ±6
Coding IQ 138.9, 95% interval 133–145. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$10.00cache read $1.00$50.00cache write $12.50922K
62.1
Good value (62.1). Cheaper per task than its benchmark results predict. Plenty of data behind it.
37 ±8
Terse (37 ±8). Generates fewer tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
169.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 5.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
 Cortecs AI
146.6
From 329 benchmarks. Plenty of data behind it.
147 ±5
Coding IQ 147.1, 95% interval 142–152. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
——1M
66.8
Good value (66.8). Cheaper per task than its benchmark results predict. Plenty of data behind it.
65 ±12
Chatty (65 ±12). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
168.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 5.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
anthropic.claude-opus-5-5
 Llmgateway
146.6
From 329 benchmarks. Plenty of data behind it.
147 ±5
Coding IQ 147.1, 95% interval 142–152. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$4.00cache read $0.20$20.00cache write $5.00Not published by the provider
66.8
Good value (66.8). Cheaper per task than its benchmark results predict. Plenty of data behind it.
65 ±12
Chatty (65 ±12). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
168.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 5.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
 OpenRouter
146.6
From 329 benchmarks. Plenty of data behind it.
147 ±5
Coding IQ 147.1, 95% interval 142–152. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$4.00cache read $0.20$20.00cache write $5.001M
66.8
Good value (66.8). Cheaper per task than its benchmark results predict. Plenty of data behind it.
65 ±12
Chatty (65 ±12). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
168.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-6.1 Sol
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
global
 OpenRouter
145.6
From 239 benchmarks. Plenty of data behind it.
135 ±16
Coding IQ 135.0, 95% interval 119–151. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.10$10.00cache write $2.50922K
68.3
Good value (68.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
51 ±11
Typical (51 ±11). Generates about as many tokens as models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate.
168.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Fable 5.1
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Fable 5.2We compared release dates and version names in our catalogue.
anthropic.claude-fable-5-1
 Llmgateway
145.3
From 253 benchmarks. Plenty of data behind it.
138 ±5
Coding IQ 137.9, 95% interval 133–143. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$10.00cache read $0.25$50.00cache write $12.50Not published by the provider
64.0
Good value (64.0). Cheaper per task than its benchmark results predict. Plenty of data behind it.
63 ±9
Chatty (63 ±9). Generates more tokens than models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate.
167.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-6.2 Sol
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
global
 OpenRouter
144.3
From 104 benchmarks. Plenty of data behind it.
139 ±9
Coding IQ 139.0, 95% interval 130–148. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.10$10.00cache write $2.50922K
69.3
Good value (69.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
48 ±9
Typical (48 ±9). Generates about as many tokens as models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate.
Not measured
Claude Opus 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
 Cortecs AI
143.9
From 389 benchmarks. Plenty of data behind it.
134 ±6
Coding IQ 133.8, 95% interval 128–140. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
——1M
64.6
Good value (64.6). Cheaper per task than its benchmark results predict. Plenty of data behind it.
61 ±9
Chatty (61 ±9). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
164.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
anthropic.claude-opus-5
 Llmgateway
143.9
From 389 benchmarks. Plenty of data behind it.
134 ±6
Coding IQ 133.8, 95% interval 128–140. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.00cache read $0.50$25.00cache write $6.25Not published by the provider
64.6
Good value (64.6). Cheaper per task than its benchmark results predict. Plenty of data behind it.
61 ±9
Chatty (61 ±9). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
164.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
 OpenRouter
143.9
From 389 benchmarks. Plenty of data behind it.
134 ±6
Coding IQ 133.8, 95% interval 128–140. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.00cache read $0.50$25.00cache write $6.251M
64.6
Good value (64.6). Cheaper per task than its benchmark results predict. Plenty of data behind it.
61 ±9
Chatty (61 ±9). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
164.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
 Requesty
143.9
From 389 benchmarks. Plenty of data behind it.
134 ±6
Coding IQ 133.8, 95% interval 128–140. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.00cache read $0.50$25.00cache write $6.251M
64.6
Good value (64.6). Cheaper per task than its benchmark results predict. Plenty of data behind it.
61 ±9
Chatty (61 ±9). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
164.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
bedrock/claude-opus-5@eu-central-1 · 🇩🇪 eu-central-1
 Requesty
143.9
From 389 benchmarks. Plenty of data behind it.
134 ±6
Coding IQ 133.8, 95% interval 128–140. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.50cache read $0.55$27.50cache write $6.8751M
64.6
Good value (64.6). Cheaper per task than its benchmark results predict. Plenty of data behind it.
61 ±9
Chatty (61 ±9). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
164.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
bedrock/claude-opus-5@eu-north-1 · 🇸🇪 eu-north-1
 Requesty
143.9
From 389 benchmarks. Plenty of data behind it.
134 ±6
Coding IQ 133.8, 95% interval 128–140. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.50cache read $0.55$27.50cache write $6.8751M
64.6
Good value (64.6). Cheaper per task than its benchmark results predict. Plenty of data behind it.
61 ±9
Chatty (61 ±9). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
164.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
bedrock/claude-opus-5@eu-west-1 · 🇮🇪 eu-west-1
 Requesty
143.9
From 389 benchmarks. Plenty of data behind it.
134 ±6
Coding IQ 133.8, 95% interval 128–140. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.50cache read $0.55$27.50cache write $6.8751M
64.6
Good value (64.6). Cheaper per task than its benchmark results predict. Plenty of data behind it.
61 ±9
Chatty (61 ±9). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
164.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
bedrock/claude-opus-5@eu-west-3 · 🇫🇷 eu-west-3
 Requesty
143.9
From 389 benchmarks. Plenty of data behind it.
134 ±6
Coding IQ 133.8, 95% interval 128–140. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.50cache read $0.55$27.50cache write $6.8751M
64.6
Good value (64.6). Cheaper per task than its benchmark results predict. Plenty of data behind it.
61 ±9
Chatty (61 ±9). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
164.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 5.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
 Cortecs AI
143.9
From 270 benchmarks. Plenty of data behind it.
140 ±5
Coding IQ 140.0, 95% interval 135–145. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
——1M
66.7
Good value (66.7). Cheaper per task than its benchmark results predict. Plenty of data behind it.
38 ±9
Terse (38 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
166.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 5.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
anthropic.claude-sonnet-5-5
 Llmgateway
143.9
From 270 benchmarks. Plenty of data behind it.
140 ±5
Coding IQ 140.0, 95% interval 135–145. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.10$10.00cache write $2.50Not published by the provider
66.7
Good value (66.7). Cheaper per task than its benchmark results predict. Plenty of data behind it.
38 ±9
Terse (38 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
166.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 5.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
 OpenRouter
143.9
From 270 benchmarks. Plenty of data behind it.
140 ±5
Coding IQ 140.0, 95% interval 135–145. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.10$10.00cache write $2.501M
66.7
Good value (66.7). Cheaper per task than its benchmark results predict. Plenty of data behind it.
38 ±9
Terse (38 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
166.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Fable 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Fable 5.2We compared release dates and version names in our catalogue.
anthropic.claude-fable-5
 Llmgateway
143.0
From 383 benchmarks. Plenty of data behind it.
132 ±5
Coding IQ 132.1, 95% interval 128–137. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$10.00cache read $1.00$50.00cache write $12.50Not published by the provider
57.1
Good value (57.1). Cheaper per task than its benchmark results predict. Plenty of data behind it.
53 ±10
Typical (53 ±10). Generates about as many tokens as models with similar coding results. Measured at default effort. A fair amount of data behind it.
164.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Fable 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Fable 5.2We compared release dates and version names in our catalogue.
bedrock/claude-fable-5@us-east-1 · 🇺🇸 us-east-1
 Requesty
143.0
From 383 benchmarks. Plenty of data behind it.
132 ±5
Coding IQ 132.1, 95% interval 128–137. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$11.00cache read $1.10$55.00cache write $13.751M
57.1
Good value (57.1). Cheaper per task than its benchmark results predict. Plenty of data behind it.
53 ±10
Typical (53 ±10). Generates about as many tokens as models with similar coding results. Measured at default effort. A fair amount of data behind it.
164.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Kimi K3.1 Pro
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
 Hugging Face
142.7
From 161 benchmarks. Plenty of data behind it.
131 ±10
Coding IQ 131.3, 95% interval 121–141. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$4.00$20.001M
49.2
Fair value (49.2). Costs per task about what its benchmark results predict. Plenty of data behind it.
51 ±9
Typical (51 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
161.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Kimi K3.1 Pro
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
us-east-1
 OpenRouter
142.7
From 161 benchmarks. Plenty of data behind it.
131 ±10
Coding IQ 131.3, 95% interval 121–141. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$4.40cache read $0.22$22.00cache write $5.501M
49.2
Fair value (49.2). Costs per task about what its benchmark results predict. Plenty of data behind it.
51 ±9
Typical (51 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
161.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Kimi K3.1 Pro
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
us-east-2
 OpenRouter
142.7
From 161 benchmarks. Plenty of data behind it.
131 ±10
Coding IQ 131.3, 95% interval 121–141. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$4.00cache read $0.20$20.00cache write $5.001M
49.2
Fair value (49.2). Costs per task about what its benchmark results predict. Plenty of data behind it.
51 ±9
Typical (51 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
161.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-6 Sol
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
global
 OpenRouter
142.5
From 210 benchmarks. Plenty of data behind it.
130 ±7
Coding IQ 129.5, 95% interval 123–136. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.20$10.00cache write $2.50922K
63.4
Good value (63.4). Cheaper per task than its benchmark results predict. Plenty of data behind it.
48 ±9
Typical (48 ±9). Generates about as many tokens as models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate.
163.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-5.6 Sol
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-6.2 SolWe compared release dates and version names in our catalogue.
global
 OpenRouter
141.6
From 504 benchmarks. Plenty of data behind it.
125 ±5
Coding IQ 125.1, 95% interval 120–130. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$4.00cache read $0.40$20.00cache write $5.00922K
59.9
Good value (59.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
41 ±8
Terse (41 ±8). Generates fewer tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
163
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 5.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT 6We compared the version names in our catalogue.
bedrock/gpt-5.5@us-east-1 · 🇺🇸 us-east-1
 Requesty
139.8
From 476 benchmarks. Plenty of data behind it.
122 ±12
Coding IQ 121.5, 95% interval 110–134. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.50cache read $0.55$33.001.1M
64.0
Good value (64.0). Cheaper per task than its benchmark results predict. Plenty of data behind it.
28 ±8
Terse (28 ±8). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
160.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 5.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT 6We compared the version names in our catalogue.
bedrock/gpt-5.5@us-east-2 · 🇺🇸 us-east-2
 Requesty
139.8
From 476 benchmarks. Plenty of data behind it.
122 ±12
Coding IQ 121.5, 95% interval 110–134. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.50cache read $0.55$33.001.1M
64.0
Good value (64.0). Cheaper per task than its benchmark results predict. Plenty of data behind it.
28 ±8
Terse (28 ±8). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
160.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.8
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
 Cortecs AI
139.7
From 478 benchmarks. Plenty of data behind it.
121 ±4
Coding IQ 120.8, 95% interval 116–125. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
——1M
52.9
Good value (52.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
40 ±10
Terse (40 ±10). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
159.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.8
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
anthropic.claude-opus-4-8
 Llmgateway
139.7
From 478 benchmarks. Plenty of data behind it.
121 ±4
Coding IQ 120.8, 95% interval 116–125. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.00cache read $0.50$25.00cache write $6.25Not published by the provider
52.9
Good value (52.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
40 ±10
Terse (40 ±10). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
159.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.8
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
 OpenRouter
139.7
From 478 benchmarks. Plenty of data behind it.
121 ±4
Coding IQ 120.8, 95% interval 116–125. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.00cache read $0.50$25.00cache write $6.251M
52.9
Good value (52.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
40 ±10
Terse (40 ±10). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
159.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.8
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
 Requesty
139.7
From 478 benchmarks. Plenty of data behind it.
121 ±4
Coding IQ 120.8, 95% interval 116–125. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.00cache read $0.50$25.00cache write $6.251M
52.9
Good value (52.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
40 ±10
Terse (40 ±10). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
159.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.8
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
bedrock/claude-opus-4-8@ap-northeast-1 · 🇯🇵 ap-northeast-1
 Requesty
139.7
From 478 benchmarks. Plenty of data behind it.
121 ±4
Coding IQ 120.8, 95% interval 116–125. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.50cache read $0.55$27.50cache write $6.8751M
52.9
Good value (52.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
40 ±10
Terse (40 ±10). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
159.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.8
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
bedrock/claude-opus-4-8@eu-central-1 · 🇩🇪 eu-central-1
 Requesty
139.7
From 478 benchmarks. Plenty of data behind it.
121 ±4
Coding IQ 120.8, 95% interval 116–125. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.50cache read $0.55$27.50cache write $6.8751M
52.9
Good value (52.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
40 ±10
Terse (40 ±10). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
159.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.8
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
bedrock/claude-opus-4-8@eu-north-1 · 🇸🇪 eu-north-1
 Requesty
139.7
From 478 benchmarks. Plenty of data behind it.
121 ±4
Coding IQ 120.8, 95% interval 116–125. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.50cache read $0.55$27.50cache write $6.8751M
52.9
Good value (52.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
40 ±10
Terse (40 ±10). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
159.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.8
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
bedrock/claude-opus-4-8@eu-west-1 · 🇮🇪 eu-west-1
 Requesty
139.7
From 478 benchmarks. Plenty of data behind it.
121 ±4
Coding IQ 120.8, 95% interval 116–125. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.50cache read $0.55$27.50cache write $6.8751M
52.9
Good value (52.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
40 ±10
Terse (40 ±10). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
159.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.8
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
bedrock/claude-opus-4-8@eu-west-3 · 🇫🇷 eu-west-3
 Requesty
139.7
From 478 benchmarks. Plenty of data behind it.
121 ±4
Coding IQ 120.8, 95% interval 116–125. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.50cache read $0.55$27.50cache write $6.8751M
52.9
Good value (52.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
40 ±10
Terse (40 ±10). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
159.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Kimi K3
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Newer version
Newer versionKimi K3.1We compared the version names in our catalogue.
 Hugging Face
139.2
From 417 benchmarks. Plenty of data behind it.
124 ±7
Coding IQ 123.8, 95% interval 117–131. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.00$15.001M
60.2
Good value (60.2). Cheaper per task than its benchmark results predict. Plenty of data behind it.
55 ±9
Typical (55 ±9). Generates about as many tokens as models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate.
158.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Kimi K3
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Newer version
Newer versionKimi K3.1We compared the version names in our catalogue.
moonshotai.kimi-k3
 Llmgateway
139.2
From 417 benchmarks. Plenty of data behind it.
124 ±7
Coding IQ 123.8, 95% interval 117–131. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.00cache read $0.30$15.00cache write $3.75Not published by the provider
60.2
Good value (60.2). Cheaper per task than its benchmark results predict. Plenty of data behind it.
55 ±9
Typical (55 ±9). Generates about as many tokens as models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate.
158.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Kimi K3
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Newer version
Newer versionKimi K3.1We compared the version names in our catalogue.
us-east-1
 OpenRouter
139.2
From 417 benchmarks. Plenty of data behind it.
124 ±7
Coding IQ 123.8, 95% interval 117–131. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.30cache read $0.33$16.50cache write $4.1251M
60.2
Good value (60.2). Cheaper per task than its benchmark results predict. Plenty of data behind it.
55 ±9
Typical (55 ±9). Generates about as many tokens as models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate.
158.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Kimi K3
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Newer version
Newer versionKimi K3.1We compared the version names in our catalogue.
us-east-2
 OpenRouter
139.2
From 417 benchmarks. Plenty of data behind it.
124 ±7
Coding IQ 123.8, 95% interval 117–131. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.00cache read $0.30$15.00cache write $3.751M
60.2
Good value (60.2). Cheaper per task than its benchmark results predict. Plenty of data behind it.
55 ±9
Typical (55 ±9). Generates about as many tokens as models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate.
158.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.7
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
 Cortecs AI
138.2
From 354 benchmarks. Plenty of data behind it.
118 ±15
Coding IQ 118.2, 95% interval 103–134. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
——1M
49.6
Fair value (49.6). Costs per task about what its benchmark results predict. Plenty of data behind it.
38 ±12
Terse (38 ±12). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
157.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.7
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
anthropic.claude-opus-4-7
 Llmgateway
138.2
From 354 benchmarks. Plenty of data behind it.
118 ±15
Coding IQ 118.2, 95% interval 103–134. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.00cache read $0.50$25.00cache write $6.25Not published by the provider
49.6
Fair value (49.6). Costs per task about what its benchmark results predict. Plenty of data behind it.
38 ±12
Terse (38 ±12). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
157.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.7
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
global
 OpenRouter
138.2
From 354 benchmarks. Plenty of data behind it.
118 ±15
Coding IQ 118.2, 95% interval 103–134. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.00cache read $0.50$25.00cache write $6.251M
49.6
Fair value (49.6). Costs per task about what its benchmark results predict. Plenty of data behind it.
38 ±12
Terse (38 ±12). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
157.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.7
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
 Requesty
138.2
From 354 benchmarks. Plenty of data behind it.
118 ±15
Coding IQ 118.2, 95% interval 103–134. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.00cache read $0.50$25.00cache write $6.251M
49.6
Fair value (49.6). Costs per task about what its benchmark results predict. Plenty of data behind it.
38 ±12
Terse (38 ±12). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
157.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.7
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
bedrock/claude-opus-4-7@eu-central-1 · 🇩🇪 eu-central-1
 Requesty
138.2
From 354 benchmarks. Plenty of data behind it.
118 ±15
Coding IQ 118.2, 95% interval 103–134. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.50cache read $0.55$27.50cache write $6.8751M
49.6
Fair value (49.6). Costs per task about what its benchmark results predict. Plenty of data behind it.
38 ±12
Terse (38 ±12). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
157.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.7
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
bedrock/claude-opus-4-7@eu-north-1 · 🇸🇪 eu-north-1
 Requesty
138.2
From 354 benchmarks. Plenty of data behind it.
118 ±15
Coding IQ 118.2, 95% interval 103–134. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.50cache read $0.55$27.50cache write $6.8751M
49.6
Fair value (49.6). Costs per task about what its benchmark results predict. Plenty of data behind it.
38 ±12
Terse (38 ±12). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
157.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.7
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
bedrock/claude-opus-4-7@eu-west-1 · 🇮🇪 eu-west-1
 Requesty
138.2
From 354 benchmarks. Plenty of data behind it.
118 ±15
Coding IQ 118.2, 95% interval 103–134. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.50cache read $0.55$27.50cache write $6.8751M
49.6
Fair value (49.6). Costs per task about what its benchmark results predict. Plenty of data behind it.
38 ±12
Terse (38 ±12). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
157.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.7
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
bedrock/claude-opus-4-7@eu-west-3 · 🇫🇷 eu-west-3
 Requesty
138.2
From 354 benchmarks. Plenty of data behind it.
118 ±15
Coding IQ 118.2, 95% interval 103–134. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.50cache read $0.55$27.50cache write $6.8751M
49.6
Fair value (49.6). Costs per task about what its benchmark results predict. Plenty of data behind it.
38 ±12
Terse (38 ±12). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
157.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
 Hugging Face
138.2
From 318 benchmarks. Plenty of data behind it.
121 ±9
Coding IQ 121.0, 95% interval 112–130. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.68$5.281M
57.7
Good value (57.7). Cheaper per task than its benchmark results predict. Plenty of data behind it.
65 ±10
Chatty (65 ±10). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
157.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
us-east-1
 OpenRouter
138.2
From 318 benchmarks. Plenty of data behind it.
121 ±9
Coding IQ 121.0, 95% interval 112–130. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.68cache read $0.312$5.28cache write $2.101M
57.7
Good value (57.7). Cheaper per task than its benchmark results predict. Plenty of data behind it.
65 ±10
Chatty (65 ±10). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
157.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.6
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
xai.grok-4.6
 Llmgateway
138.0
From 220 benchmarks. Plenty of data behind it.
120 ±11
Coding IQ 120.1, 95% interval 109–131. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.50$6.00Not published by the provider
56.0
Good value (56.0). Cheaper per task than its benchmark results predict. Plenty of data behind it.
47 ±10
Typical (47 ±10). Generates about as many tokens as models with similar coding results. Measured at high effort. A fair amount of data behind it.
157.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.7
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
xai.grok-4.7
 Llmgateway
137.7
From 249 benchmarks. Plenty of data behind it.
117 ±7
Coding IQ 117.4, 95% interval 111–124. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.50$6.00Not published by the provider
41.2
Poor value (41.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
55 ±14
Typical (55 ±14). Generates about as many tokens as models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate.
156.4
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.6
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
 Cortecs AI
136.9
From 466 benchmarks. Plenty of data behind it.
118 ±5
Coding IQ 117.9, 95% interval 113–123. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
——1M
47.2
Poor value (47.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
41 ±15
Terse (41 ±15). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
156.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.6
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
anthropic.claude-opus-4-6-v1
 Llmgateway
136.9
From 466 benchmarks. Plenty of data behind it.
118 ±5
Coding IQ 117.9, 95% interval 113–123. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.00cache read $0.50$25.00cache write $6.25Not published by the provider
47.2
Poor value (47.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
41 ±15
Terse (41 ±15). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
156.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.6
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
 OpenRouter
136.9
From 466 benchmarks. Plenty of data behind it.
118 ±5
Coding IQ 117.9, 95% interval 113–123. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.00cache read $0.50$25.00cache write $6.251M
47.2
Poor value (47.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
41 ±15
Terse (41 ±15). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
156.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.6
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Opus 5.5We compared release dates and version names in our catalogue.
 Requesty
136.9
From 466 benchmarks. Plenty of data behind it.
118 ±5
Coding IQ 117.9, 95% interval 113–123. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.00cache read $0.50$25.00cache write $6.251M
47.2
Poor value (47.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
41 ±15
Terse (41 ±15). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
156.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 5.4
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT 6We compared the version names in our catalogue.
bedrock/gpt-5.4@us-east-1 · 🇺🇸 us-east-1
 Requesty
136.8
From 489 benchmarks. Plenty of data behind it.
112 ±8
Coding IQ 112.0, 95% interval 104–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.75cache read $0.275$16.501.1M
60.1
Good value (60.1). Cheaper per task than its benchmark results predict. Plenty of data behind it.
28 ±8
Terse (28 ±8). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
157.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 5.4
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT 6We compared the version names in our catalogue.
bedrock/gpt-5.4@us-east-2 · 🇺🇸 us-east-2
 Requesty
136.8
From 489 benchmarks. Plenty of data behind it.
112 ±8
Coding IQ 112.0, 95% interval 104–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.75cache read $0.275$16.501.1M
60.1
Good value (60.1). Cheaper per task than its benchmark results predict. Plenty of data behind it.
28 ±8
Terse (28 ±8). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
157.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 5.4
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT 6We compared the version names in our catalogue.
bedrock/gpt-5.4@us-west-2 · 🇺🇸 us-west-2
 Requesty
136.8
From 489 benchmarks. Plenty of data behind it.
112 ±8
Coding IQ 112.0, 95% interval 104–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.75cache read $0.275$16.501.1M
60.1
Good value (60.1). Cheaper per task than its benchmark results predict. Plenty of data behind it.
28 ±8
Terse (28 ±8). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
157.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Sonnet 5.5We compared release dates and version names in our catalogue.
 Cortecs AI
136.3
From 360 benchmarks. Plenty of data behind it.
115 ±5
Coding IQ 115.2, 95% interval 111–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
——1M
37.4
Poor value (37.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
57 ±9
Chatty (57 ±9). Generates more tokens than models with similar coding results. Measured at medium effort. Little data behind it, so treat it as a rough estimate.
156.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Sonnet 5.5We compared release dates and version names in our catalogue.
anthropic.claude-sonnet-5
 Llmgateway
136.3
From 360 benchmarks. Plenty of data behind it.
115 ±5
Coding IQ 115.2, 95% interval 111–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.20$10.00cache write $2.50Not published by the provider
37.4
Poor value (37.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
57 ±9
Chatty (57 ±9). Generates more tokens than models with similar coding results. Measured at medium effort. Little data behind it, so treat it as a rough estimate.
156.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Sonnet 5.5We compared release dates and version names in our catalogue.
global
 OpenRouter
136.3
From 360 benchmarks. Plenty of data behind it.
115 ±5
Coding IQ 115.2, 95% interval 111–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.20$10.00cache write $2.501M
37.4
Poor value (37.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
57 ±9
Chatty (57 ±9). Generates more tokens than models with similar coding results. Measured at medium effort. Little data behind it, so treat it as a rough estimate.
156.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Sonnet 5.5We compared release dates and version names in our catalogue.
 Requesty
136.3
From 360 benchmarks. Plenty of data behind it.
115 ±5
Coding IQ 115.2, 95% interval 111–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.20$10.00cache write $2.501M
37.4
Poor value (37.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
57 ±9
Chatty (57 ±9). Generates more tokens than models with similar coding results. Measured at medium effort. Little data behind it, so treat it as a rough estimate.
156.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Sonnet 5.5We compared release dates and version names in our catalogue.
bedrock/claude-sonnet-5@ap-southeast-2 · 🇦🇺 ap-southeast-2
 Requesty
136.3
From 360 benchmarks. Plenty of data behind it.
115 ±5
Coding IQ 115.2, 95% interval 111–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.20cache read $0.22$11.00cache write $2.751M
37.4
Poor value (37.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
57 ±9
Chatty (57 ±9). Generates more tokens than models with similar coding results. Measured at medium effort. Little data behind it, so treat it as a rough estimate.
156.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Sonnet 5.5We compared release dates and version names in our catalogue.
bedrock/claude-sonnet-5@eu-central-1 · 🇩🇪 eu-central-1
 Requesty
136.3
From 360 benchmarks. Plenty of data behind it.
115 ±5
Coding IQ 115.2, 95% interval 111–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.20cache read $0.22$11.00cache write $2.751M
37.4
Poor value (37.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
57 ±9
Chatty (57 ±9). Generates more tokens than models with similar coding results. Measured at medium effort. Little data behind it, so treat it as a rough estimate.
156.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Sonnet 5.5We compared release dates and version names in our catalogue.
bedrock/claude-sonnet-5@eu-north-1 · 🇸🇪 eu-north-1
 Requesty
136.3
From 360 benchmarks. Plenty of data behind it.
115 ±5
Coding IQ 115.2, 95% interval 111–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.20cache read $0.22$11.00cache write $2.751M
37.4
Poor value (37.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
57 ±9
Chatty (57 ±9). Generates more tokens than models with similar coding results. Measured at medium effort. Little data behind it, so treat it as a rough estimate.
156.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Sonnet 5.5We compared release dates and version names in our catalogue.
bedrock/claude-sonnet-5@eu-west-1 · 🇮🇪 eu-west-1
 Requesty
136.3
From 360 benchmarks. Plenty of data behind it.
115 ±5
Coding IQ 115.2, 95% interval 111–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.20cache read $0.22$11.00cache write $2.751M
37.4
Poor value (37.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
57 ±9
Chatty (57 ±9). Generates more tokens than models with similar coding results. Measured at medium effort. Little data behind it, so treat it as a rough estimate.
156.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Sonnet 5.5We compared release dates and version names in our catalogue.
bedrock/claude-sonnet-5@eu-west-2 · 🇬🇧 eu-west-2
 Requesty
136.3
From 360 benchmarks. Plenty of data behind it.
115 ±5
Coding IQ 115.2, 95% interval 111–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.20cache read $0.22$11.00cache write $2.751M
37.4
Poor value (37.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
57 ±9
Chatty (57 ±9). Generates more tokens than models with similar coding results. Measured at medium effort. Little data behind it, so treat it as a rough estimate.
156.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Sonnet 5.5We compared release dates and version names in our catalogue.
bedrock/claude-sonnet-5@us-east-1 · 🇺🇸 us-east-1
 Requesty
136.3
From 360 benchmarks. Plenty of data behind it.
115 ±5
Coding IQ 115.2, 95% interval 111–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.20cache read $0.22$11.00cache write $2.751M
37.4
Poor value (37.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
57 ±9
Chatty (57 ±9). Generates more tokens than models with similar coding results. Measured at medium effort. Little data behind it, so treat it as a rough estimate.
156.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Sonnet 5.5We compared release dates and version names in our catalogue.
bedrock/claude-sonnet-5@us-east-2 · 🇺🇸 us-east-2
 Requesty
136.3
From 360 benchmarks. Plenty of data behind it.
115 ±5
Coding IQ 115.2, 95% interval 111–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.20cache read $0.22$11.00cache write $2.751M
37.4
Poor value (37.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
57 ±9
Chatty (57 ±9). Generates more tokens than models with similar coding results. Measured at medium effort. Little data behind it, so treat it as a rough estimate.
156.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Sonnet 5.5We compared release dates and version names in our catalogue.
bedrock/claude-sonnet-5@us-west-2 · 🇺🇸 us-west-2
 Requesty
136.3
From 360 benchmarks. Plenty of data behind it.
115 ±5
Coding IQ 115.2, 95% interval 111–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.20cache read $0.22$11.00cache write $2.751M
37.4
Poor value (37.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
57 ±9
Chatty (57 ±9). Generates more tokens than models with similar coding results. Measured at medium effort. Little data behind it, so treat it as a rough estimate.
156.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API

Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence)

How this data works