Skip to content

Listings

All listings: Amazon Web Services

Every listing for the models on page 2 of 9 of Amazon Web Services, including each model's other versions and routes. Back to Amazon Web Services

Sold by Amazon Web Services

104 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
GPT-6 Luna
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
openai.gpt-6-luna
135.6
From 227 benchmarks. Plenty of data behind it.
117 ±6
Coding IQ 116.9, 95% interval 111–123. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.11cache read $0.011$0.55cache write $0.1375922K
63.4
Good value (63.4). 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.
156.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-6 Luna
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
global.openai.gpt-6-luna · global
135.6
From 227 benchmarks. Plenty of data behind it.
117 ±6
Coding IQ 116.9, 95% interval 111–123. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.10cache read $0.01$0.50cache write $0.125922K
63.4
Good value (63.4). 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.
156.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-6 Luna
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
us.openai.gpt-6-luna · 🇺🇸 us
135.6
From 227 benchmarks. Plenty of data behind it.
117 ±6
Coding IQ 116.9, 95% interval 111–123. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.11cache read $0.011$0.55cache write $0.1375922K
63.4
Good value (63.4). 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.
156.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-5.6 Luna
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-6 LunaWe compared release dates and version names in our catalogue.
openai.gpt-5.6-luna
135.2
From 344 benchmarks. Plenty of data behind it.
112 ±10
Coding IQ 112.4, 95% interval 102–123. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.22cache read $0.022$1.32cache write $0.275922K
66.2
Good value (66.2). Cheaper per task than its benchmark results predict. Plenty of data behind it.
52 ±8
Typical (52 ±8). Generates about as many tokens as models with similar coding results. Measured at max effort. A fair amount of data behind it.
156.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-5.6 Luna
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-6 LunaWe compared release dates and version names in our catalogue.
global.openai.gpt-5.6-luna · global
135.2
From 344 benchmarks. Plenty of data behind it.
112 ±10
Coding IQ 112.4, 95% interval 102–123. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.20cache read $0.02$1.20cache write $0.25922K
66.2
Good value (66.2). Cheaper per task than its benchmark results predict. Plenty of data behind it.
52 ±8
Typical (52 ±8). Generates about as many tokens as models with similar coding results. Measured at max effort. A fair amount of data behind it.
156.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-5.6 Luna
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-6 LunaWe compared release dates and version names in our catalogue.
us-gov.openai.gpt-5.6-luna · 🇺🇸 us-gov
135.2
From 344 benchmarks. Plenty of data behind it.
112 ±10
Coding IQ 112.4, 95% interval 102–123. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.264cache read $0.0264$1.584cache write $0.33922K
66.2
Good value (66.2). Cheaper per task than its benchmark results predict. Plenty of data behind it.
52 ±8
Typical (52 ±8). Generates about as many tokens as models with similar coding results. Measured at max effort. A fair amount of data behind it.
156.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-5.6 Luna
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-6 LunaWe compared release dates and version names in our catalogue.
us.openai.gpt-5.6-luna · 🇺🇸 us
135.2
From 344 benchmarks. Plenty of data behind it.
112 ±10
Coding IQ 112.4, 95% interval 102–123. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.22cache read $0.022$1.32cache write $0.275922K
66.2
Good value (66.2). Cheaper per task than its benchmark results predict. Plenty of data behind it.
52 ±8
Typical (52 ±8). Generates about as many tokens as models with similar coding results. Measured at max effort. A fair amount of data behind it.
156.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Haiku 5.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
anthropic.claude-haiku-5-5
134.6
From 230 benchmarks. Plenty of data behind it.
124 ±6
Coding IQ 123.6, 95% interval 118–129. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.10cache read $0.01$0.50cache write $0.1251M
62.1
Good value (62.1). Cheaper per task than its benchmark results predict. Plenty of data behind it.
49 ±9
Typical (49 ±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.
160.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Haiku 5.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
apac.anthropic.claude-haiku-5-5 · apac
134.6
From 230 benchmarks. Plenty of data behind it.
124 ±6
Coding IQ 123.6, 95% interval 118–129. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.11cache read $0.011$0.55cache write $0.13751M
62.1
Good value (62.1). Cheaper per task than its benchmark results predict. Plenty of data behind it.
49 ±9
Typical (49 ±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.
160.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Haiku 5.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
au.anthropic.claude-haiku-5-5 · 🇦🇺 au
134.6
From 230 benchmarks. Plenty of data behind it.
124 ±6
Coding IQ 123.6, 95% interval 118–129. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.11cache read $0.011$0.55cache write $0.13751M
62.1
Good value (62.1). Cheaper per task than its benchmark results predict. Plenty of data behind it.
49 ±9
Typical (49 ±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.
160.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Haiku 5.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
ca.anthropic.claude-haiku-5-5 · 🇨🇦 ca
134.6
From 230 benchmarks. Plenty of data behind it.
124 ±6
Coding IQ 123.6, 95% interval 118–129. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.11cache read $0.011$0.55cache write $0.13751M
62.1
Good value (62.1). Cheaper per task than its benchmark results predict. Plenty of data behind it.
49 ±9
Typical (49 ±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.
160.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Haiku 5.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
eu.anthropic.claude-haiku-5-5 · 🇪🇺 eu
134.6
From 230 benchmarks. Plenty of data behind it.
124 ±6
Coding IQ 123.6, 95% interval 118–129. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.11cache read $0.011$0.55cache write $0.13751M
62.1
Good value (62.1). Cheaper per task than its benchmark results predict. Plenty of data behind it.
49 ±9
Typical (49 ±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.
160.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Haiku 5.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
global.anthropic.claude-haiku-5-5 · global
134.6
From 230 benchmarks. Plenty of data behind it.
124 ±6
Coding IQ 123.6, 95% interval 118–129. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.10cache read $0.01$0.50cache write $0.1251M
62.1
Good value (62.1). Cheaper per task than its benchmark results predict. Plenty of data behind it.
49 ±9
Typical (49 ±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.
160.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Haiku 5.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
jp.anthropic.claude-haiku-5-5 · 🇯🇵 jp
134.6
From 230 benchmarks. Plenty of data behind it.
124 ±6
Coding IQ 123.6, 95% interval 118–129. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.11cache read $0.011$0.55cache write $0.13751M
62.1
Good value (62.1). Cheaper per task than its benchmark results predict. Plenty of data behind it.
49 ±9
Typical (49 ±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.
160.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Haiku 5.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
us-gov.anthropic.claude-haiku-5-5 · 🇺🇸 us-gov
134.6
From 230 benchmarks. Plenty of data behind it.
124 ±6
Coding IQ 123.6, 95% interval 118–129. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.12cache read $0.012$0.60cache write $0.151M
62.1
Good value (62.1). Cheaper per task than its benchmark results predict. Plenty of data behind it.
49 ±9
Typical (49 ±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.
160.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Haiku 5.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
us.anthropic.claude-haiku-5-5 · 🇺🇸 us
134.6
From 230 benchmarks. Plenty of data behind it.
124 ±6
Coding IQ 123.6, 95% interval 118–129. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.11cache read $0.011$0.55cache write $0.13751M
62.1
Good value (62.1). Cheaper per task than its benchmark results predict. Plenty of data behind it.
49 ±9
Typical (49 ±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.
160.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.5
🇺🇸
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-4-5-20251101-v1:0 · 20251101
134.0
From 384 benchmarks. Plenty of data behind it.
113 ±5
Coding IQ 112.8, 95% interval 108–118. 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 $6.25200K
46.0
Poor value (46.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
43 ±10
Terse (43 ±10). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
151.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.5
🇺🇸
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-4-5-v1:0 · global
134.0
From 384 benchmarks. Plenty of data behind it.
113 ±5
Coding IQ 112.8, 95% interval 108–118. 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
46.0
Poor value (46.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
43 ±10
Terse (43 ±10). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
151.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.5
🇺🇸
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-4-5-v1:0 · regional
134.0
From 384 benchmarks. Plenty of data behind it.
113 ±5
Coding IQ 112.8, 95% interval 108–118. 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
46.0
Poor value (46.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
43 ±10
Terse (43 ±10). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
151.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.5
🇺🇸
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-4-5-20251101-v1:0 · 20251101 · 🇪🇺 eu
134.0
From 384 benchmarks. Plenty of data behind it.
113 ±5
Coding IQ 112.8, 95% interval 108–118. 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 $6.875200K
46.0
Poor value (46.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
43 ±10
Terse (43 ±10). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
151.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.5
🇺🇸
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-4-5-20251101-v1:0 · 20251101 · global
134.0
From 384 benchmarks. Plenty of data behind it.
113 ±5
Coding IQ 112.8, 95% interval 108–118. 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 $6.25200K
46.0
Poor value (46.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
43 ±10
Terse (43 ±10). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
151.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.5
🇺🇸
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-4-5-20251101-v1:0 · 20251101 · 🇺🇸 us
134.0
From 384 benchmarks. Plenty of data behind it.
113 ±5
Coding IQ 112.8, 95% interval 108–118. 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 $6.875200K
46.0
Poor value (46.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
43 ±10
Terse (43 ±10). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
151.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.5
🇺🇸
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.
claude-opus-4-5-20251101 · 20251101
134.0
From 384 benchmarks. Plenty of data behind it.
113 ±5
Coding IQ 112.8, 95% interval 108–118. 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
46.0
Poor value (46.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
43 ±10
Terse (43 ±10). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
151.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.6
🇺🇸
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-4-6
133.8
From 469 benchmarks. Plenty of data behind it.
108 ±6
Coding IQ 108.4, 95% interval 103–114. 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
35.4
Poor value (35.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
71 ±8
Chatty (71 ±8). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
152.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.6
🇺🇸
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-4-6-v1:0 · global
133.8
From 469 benchmarks. Plenty of data behind it.
108 ±6
Coding IQ 108.4, 95% interval 103–114. 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
35.4
Poor value (35.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
71 ±8
Chatty (71 ±8). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
152.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.6
🇺🇸
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-4-6-v1:0 · regional
133.8
From 469 benchmarks. Plenty of data behind it.
108 ±6
Coding IQ 108.4, 95% interval 103–114. 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 $4.125Not published by the provider
35.4
Poor value (35.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
71 ±8
Chatty (71 ±8). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
152.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.6
🇺🇸
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-4-6 · apac
133.8
From 469 benchmarks. Plenty of data behind it.
108 ±6
Coding IQ 108.4, 95% interval 103–114. 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
35.4
Poor value (35.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
71 ±8
Chatty (71 ±8). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
152.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.6
🇺🇸
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-4-6 · 🇦🇺 au
133.8
From 469 benchmarks. Plenty of data behind it.
108 ±6
Coding IQ 108.4, 95% interval 103–114. 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
35.4
Poor value (35.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
71 ±8
Chatty (71 ±8). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
152.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.6
🇺🇸
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-4-6 · 🇪🇺 eu
133.8
From 469 benchmarks. Plenty of data behind it.
108 ±6
Coding IQ 108.4, 95% interval 103–114. 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
35.4
Poor value (35.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
71 ±8
Chatty (71 ±8). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
152.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.6
🇺🇸
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-4-6 · global
133.8
From 469 benchmarks. Plenty of data behind it.
108 ±6
Coding IQ 108.4, 95% interval 103–114. 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
35.4
Poor value (35.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
71 ±8
Chatty (71 ±8). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
152.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.6
🇺🇸
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-4-6 · 🇯🇵 jp
133.8
From 469 benchmarks. Plenty of data behind it.
108 ±6
Coding IQ 108.4, 95% interval 103–114. 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
35.4
Poor value (35.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
71 ±8
Chatty (71 ±8). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
152.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.6
🇺🇸
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-4-6 · 🇺🇸 us
133.8
From 469 benchmarks. Plenty of data behind it.
108 ±6
Coding IQ 108.4, 95% interval 103–114. 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
35.4
Poor value (35.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
71 ±8
Chatty (71 ±8). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
152.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.6
🇺🇸
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.
133.8
From 469 benchmarks. Plenty of data behind it.
108 ±6
Coding IQ 108.4, 95% interval 103–114. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.00$15.00Not published by the provider
35.4
Poor value (35.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
71 ±8
Chatty (71 ±8). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
152.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.6
🇺🇸
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-4-6-v1 · 🇪🇺 eu
133.8
From 469 benchmarks. Plenty of data behind it.
108 ±6
Coding IQ 108.4, 95% interval 103–114. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.30$16.50Not published by the provider
35.4
Poor value (35.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
71 ±8
Chatty (71 ±8). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
152.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.6
🇺🇸
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-4-6-v1:0 · 🇪🇺 eu
133.8
From 469 benchmarks. Plenty of data behind it.
108 ±6
Coding IQ 108.4, 95% interval 103–114. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.30$16.50Not published by the provider
35.4
Poor value (35.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
71 ±8
Chatty (71 ±8). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
152.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.6
🇺🇸
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-4-6-v1 · 🇺🇸 us
133.8
From 469 benchmarks. Plenty of data behind it.
108 ±6
Coding IQ 108.4, 95% interval 103–114. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.30$16.50Not published by the provider
35.4
Poor value (35.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
71 ±8
Chatty (71 ±8). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
152.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.6
🇺🇸
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-4-6-v1:0 · 🇺🇸 us
133.8
From 469 benchmarks. Plenty of data behind it.
108 ±6
Coding IQ 108.4, 95% interval 103–114. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.30$16.50Not published by the provider
35.4
Poor value (35.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
71 ±8
Chatty (71 ±8). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
152.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.6
🇺🇸
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-4-6-v1
133.8
From 469 benchmarks. Plenty of data behind it.
108 ±6
Coding IQ 108.4, 95% interval 103–114. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.00$15.00Not published by the provider
35.4
Poor value (35.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
71 ±8
Chatty (71 ±8). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
152.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.6
🇺🇸
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-4-6-v1:0
133.8
From 469 benchmarks. Plenty of data behind it.
108 ±6
Coding IQ 108.4, 95% interval 103–114. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.00$15.00Not published by the provider
35.4
Poor value (35.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
71 ±8
Chatty (71 ±8). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
152.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.6
🇺🇸
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.
claude-sonnet-4-6-v1
133.8
From 469 benchmarks. Plenty of data behind it.
108 ±6
Coding IQ 108.4, 95% interval 103–114. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.00$15.00Not published by the provider
35.4
Poor value (35.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
71 ±8
Chatty (71 ±8). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
152.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.5
🇺🇸
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-4-5-20250929-v1:0 · 20250929 · global
129.7
From 442 benchmarks. Plenty of data behind it.
107 ±7
Coding IQ 107.2, 95% interval 101–114. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.00>200k $6.00cache read $0.30batch $1.50$15.00>200k $22.50cache write $3.75batch $7.50200K
40.2
Poor value (40.2). Costs more 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 default effort. A fair amount of data behind it.
147.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.5
🇺🇸
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-4-5-20250929-v1:0 · 20250929 · regional
129.7
From 442 benchmarks. Plenty of data behind it.
107 ±7
Coding IQ 107.2, 95% interval 101–114. 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 $4.125Not published by the provider
40.2
Poor value (40.2). Costs more 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 default effort. A fair amount of data behind it.
147.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.5
🇺🇸
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-4-5-20250929-v1:0 · 20250929 · 🇦🇺 au
129.7
From 442 benchmarks. Plenty of data behind it.
107 ±7
Coding IQ 107.2, 95% interval 101–114. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.30>200k $6.60cache read $0.33batch $1.65$16.50>200k $24.75cache write $4.125batch $8.25200K
40.2
Poor value (40.2). Costs more 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 default effort. A fair amount of data behind it.
147.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.5
🇺🇸
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-4-5-20250929-v1:0 · 20250929 · 🇪🇺 eu
129.7
From 442 benchmarks. Plenty of data behind it.
107 ±7
Coding IQ 107.2, 95% interval 101–114. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.30>200k $6.60cache read $0.33batch $1.65$16.50>200k $24.75cache write $4.125batch $8.25200K
40.2
Poor value (40.2). Costs more 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 default effort. A fair amount of data behind it.
147.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.5
🇺🇸
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-4-5-20250929-v1:0 · 20250929 · 🇯🇵 jp
129.7
From 442 benchmarks. Plenty of data behind it.
107 ±7
Coding IQ 107.2, 95% interval 101–114. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.30>200k $6.60cache read $0.33batch $1.65$16.50>200k $24.75cache write $4.125batch $8.25200K
40.2
Poor value (40.2). Costs more 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 default effort. A fair amount of data behind it.
147.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.5
🇺🇸
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-4-5-20250929-v1:0 · 20250929 · 🇺🇸 us-gov
129.7
From 442 benchmarks. Plenty of data behind it.
107 ±7
Coding IQ 107.2, 95% interval 101–114. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.60>200k $7.20cache read $0.36$18.00>200k $27.00cache write $4.50200K
40.2
Poor value (40.2). Costs more 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 default effort. A fair amount of data behind it.
147.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.5
🇺🇸
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-4-5-20250929-v1:0 · 20250929 · 🇺🇸 us
129.7
From 442 benchmarks. Plenty of data behind it.
107 ±7
Coding IQ 107.2, 95% interval 101–114. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.30>200k $6.60cache read $0.33batch $1.65$16.50>200k $24.75cache write $4.125batch $8.25200K
40.2
Poor value (40.2). Costs more 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 default effort. A fair amount of data behind it.
147.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.5
🇺🇸
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.
claude-sonnet-4-5-20250929-v1:0 · 20250929
129.7
From 442 benchmarks. Plenty of data behind it.
107 ±7
Coding IQ 107.2, 95% interval 101–114. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.00>200k $6.00cache read $0.30batch $1.50$15.00>200k $22.50cache write $3.75batch $7.50200K
40.2
Poor value (40.2). Costs more 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 default effort. A fair amount of data behind it.
147.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.5
🇺🇸
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.
claude-sonnet-4-5-20250929 · 20250929
129.7
From 442 benchmarks. Plenty of data behind it.
107 ±7
Coding IQ 107.2, 95% interval 101–114. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.00$15.00Not published by the provider
40.2
Poor value (40.2). Costs more 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 default effort. A fair amount of data behind it.
147.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGLM 5.3We compared release dates and version names in our catalogue.
zai.glm-5
129.7
From 306 benchmarks. Plenty of data behind it.
107 ±5
Coding IQ 106.7, 95% interval 102–112. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.00batch $0.50$3.20batch $1.60200K
49.7
Fair value (49.7). Costs per task about what 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 default effort. Little data behind it, so treat it as a rough estimate.
146.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Kimi K2.5
🇨🇳
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-k2.5
128.5
From 401 benchmarks. Plenty of data behind it.
103 ±5
Coding IQ 102.9, 95% interval 98–108. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.60batch $0.30$3.00batch $1.50256K
48.2
Fair value (48.2). Costs per task about what its benchmark results predict. Plenty of data behind it.
42 ±9
Terse (42 ±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.
148.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.1
🇺🇸
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-4-1-20250805-v1:0 · 20250805 · regional
128.3
From 249 benchmarks. Plenty of data behind it.
109 ±7
Coding IQ 108.6, 95% interval 102–115. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$15.00cache read $1.50$75.00cache write $18.75Not published by the provider
34.6
Poor value (34.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
35 ±9
Terse (35 ±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.
144.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.1
🇺🇸
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.
128.3
From 249 benchmarks. Plenty of data behind it.
109 ±7
Coding IQ 108.6, 95% interval 102–115. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$15.00$75.00Not published by the provider
34.6
Poor value (34.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
35 ±9
Terse (35 ±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.
144.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.1
🇺🇸
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-4-1-20250805-v1:0 · 20250805 · 🇪🇺 eu
128.3
From 249 benchmarks. Plenty of data behind it.
109 ±7
Coding IQ 108.6, 95% interval 102–115. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$15.00cache read $1.50$75.00cache write $18.75200K
34.6
Poor value (34.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
35 ±9
Terse (35 ±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.
144.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.1
🇺🇸
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-4-1-20250805-v1:0 · 20250805 · 🇺🇸 us
128.3
From 249 benchmarks. Plenty of data behind it.
109 ±7
Coding IQ 108.6, 95% interval 102–115. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$15.00cache read $1.50$75.00cache write $18.75200K
34.6
Poor value (34.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
35 ±9
Terse (35 ±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.
144.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.1
🇺🇸
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.
claude-opus-4-1-20250805 · 20250805
128.3
From 249 benchmarks. Plenty of data behind it.
109 ±7
Coding IQ 108.6, 95% interval 102–115. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$15.00$75.00Not published by the provider
34.6
Poor value (34.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
35 ±9
Terse (35 ±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.
144.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Gemma 4 31B IT
🇺🇸
Maker headquartered in US, 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.
bedrock_mantle/google.gemma-4-31b
128.3
From 333 benchmarks. Plenty of data behind it.
102 ±7
Coding IQ 101.7, 95% interval 94–109. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.14batch $0.07$0.40batch $0.20256K
61.9
Good value (61.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
43 ±9
Terse (43 ±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.
144.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4
🇺🇸
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-4-20250514-v1:0 · 20250514 · regional
127.4
From 296 benchmarks. Plenty of data behind it.
102 ±6
Coding IQ 102.3, 95% interval 96–109. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$15.00cache read $1.50$75.00cache write $18.75Not published by the provider
26.0
Poor value (26.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
43 ±9
Terse (43 ±9). Generates fewer tokens than models with similar coding results. Measured at high effort. Little data behind it, so treat it as a rough estimate.
142.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4
🇺🇸
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.
127.4
From 296 benchmarks. Plenty of data behind it.
102 ±6
Coding IQ 102.3, 95% interval 96–109. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$15.00$75.00Not published by the provider
26.0
Poor value (26.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
43 ±9
Terse (43 ±9). Generates fewer tokens than models with similar coding results. Measured at high effort. Little data behind it, so treat it as a rough estimate.
142.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4
🇺🇸
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-4-20250514-v1:0 · 20250514 · 🇪🇺 eu
127.4
From 296 benchmarks. Plenty of data behind it.
102 ±6
Coding IQ 102.3, 95% interval 96–109. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$15.00cache read $1.50$75.00cache write $18.75200K
26.0
Poor value (26.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
43 ±9
Terse (43 ±9). Generates fewer tokens than models with similar coding results. Measured at high effort. Little data behind it, so treat it as a rough estimate.
142.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4
🇺🇸
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-4-20250514-v1:0 · 20250514 · 🇺🇸 us
127.4
From 296 benchmarks. Plenty of data behind it.
102 ±6
Coding IQ 102.3, 95% interval 96–109. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$15.00cache read $1.50$75.00cache write $18.75200K
26.0
Poor value (26.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
43 ±9
Terse (43 ±9). Generates fewer tokens than models with similar coding results. Measured at high effort. Little data behind it, so treat it as a rough estimate.
142.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4
🇺🇸
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-4-20250514-v1:0 · 20250514
127.4
From 296 benchmarks. Plenty of data behind it.
102 ±6
Coding IQ 102.3, 95% interval 96–109. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$15.00cache read $1.50$75.00cache write $18.75200K
26.0
Poor value (26.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
43 ±9
Terse (43 ±9). Generates fewer tokens than models with similar coding results. Measured at high effort. Little data behind it, so treat it as a rough estimate.
142.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4
🇺🇸
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.
claude-opus-4-20250514 · 20250514
127.4
From 296 benchmarks. Plenty of data behind it.
102 ±6
Coding IQ 102.3, 95% interval 96–109. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$15.00$75.00Not published by the provider
26.0
Poor value (26.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
43 ±9
Terse (43 ±9). Generates fewer tokens than models with similar coding results. Measured at high effort. Little data behind it, so treat it as a rough estimate.
142.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4
🇺🇸
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-4-20250514-v1:0 · 20250514 · global
127.0
From 321 benchmarks. Plenty of data behind it.
99 ±7
Coding IQ 99.2, 95% interval 92–106. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.00>200k $6.00cache read $0.30$15.00>200k $22.50cache write $3.75200K
42.3
Poor value (42.3). Costs more per task than its benchmark results predict. Plenty of data behind it.
47 ±9
Typical (47 ±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.
141.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4
🇺🇸
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-4-20250514-v1:0 · 20250514 · regional
127.0
From 321 benchmarks. Plenty of data behind it.
99 ±7
Coding IQ 99.2, 95% interval 92–106. 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
42.3
Poor value (42.3). Costs more per task than its benchmark results predict. Plenty of data behind it.
47 ±9
Typical (47 ±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.
141.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4
🇺🇸
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.
127.0
From 321 benchmarks. Plenty of data behind it.
99 ±7
Coding IQ 99.2, 95% interval 92–106. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.00$15.00Not published by the provider
42.3
Poor value (42.3). Costs more per task than its benchmark results predict. Plenty of data behind it.
47 ±9
Typical (47 ±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.
141.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4
🇺🇸
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-4-20250514-v1:0 · 20250514 · apac
127.0
From 321 benchmarks. Plenty of data behind it.
99 ±7
Coding IQ 99.2, 95% interval 92–106. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.00>200k $6.00cache read $0.30$15.00>200k $22.50cache write $3.75200K
42.3
Poor value (42.3). Costs more per task than its benchmark results predict. Plenty of data behind it.
47 ±9
Typical (47 ±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.
141.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4
🇺🇸
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-4-20250514-v1:0 · 20250514 · 🇪🇺 eu
127.0
From 321 benchmarks. Plenty of data behind it.
99 ±7
Coding IQ 99.2, 95% interval 92–106. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.00>200k $6.00cache read $0.30$15.00>200k $22.50cache write $3.75200K
42.3
Poor value (42.3). Costs more per task than its benchmark results predict. Plenty of data behind it.
47 ±9
Typical (47 ±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.
141.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4
🇺🇸
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-4-20250514-v1:0 · 20250514 · 🇺🇸 us
127.0
From 321 benchmarks. Plenty of data behind it.
99 ±7
Coding IQ 99.2, 95% interval 92–106. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.00>200k $6.00cache read $0.30$15.00>200k $22.50cache write $3.75200K
42.3
Poor value (42.3). Costs more per task than its benchmark results predict. Plenty of data behind it.
47 ±9
Typical (47 ±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.
141.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4
🇺🇸
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-4-20250514-v1:0 · 20250514
127.0
From 321 benchmarks. Plenty of data behind it.
99 ±7
Coding IQ 99.2, 95% interval 92–106. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.00>200k $6.00cache read $0.30$15.00>200k $22.50cache write $3.75200K
42.3
Poor value (42.3). Costs more per task than its benchmark results predict. Plenty of data behind it.
47 ±9
Typical (47 ±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.
141.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4
🇺🇸
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.
claude-sonnet-4-20250514 · 20250514
127.0
From 321 benchmarks. Plenty of data behind it.
99 ±7
Coding IQ 99.2, 95% interval 92–106. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.00$15.00Not published by the provider
42.3
Poor value (42.3). Costs more per task than its benchmark results predict. Plenty of data behind it.
47 ±9
Typical (47 ±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.
141.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 4.7
🇨🇳
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 versionGLM 5.3We compared release dates and version names in our catalogue.
zai.glm-4.7
127.0
From 234 benchmarks. Plenty of data behind it.
104 ±5
Coding IQ 103.5, 95% interval 98–109. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.60batch $0.30$2.20batch $1.10203K
41.0
Poor value (41.0). Costs more 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 default effort. Little data behind it, so treat it as a rough estimate.
143.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
DeepSeek V3.2
🇨🇳
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 versionDeepSeek V4We compared the version names in our catalogue.
125.0
From 247 benchmarks. Plenty of data behind it.
101 ±7
Coding IQ 101.2, 95% interval 94–108. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.62batch $0.31$1.85batch $0.925156K
63.8
Good value (63.8). Cheaper per task than its benchmark results predict. Plenty of data behind it.
Not measured
146.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
DeepSeek V3.2
🇨🇳
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 versionDeepSeek V4We compared the version names in our catalogue.
eu.deepseek.v3.2 · 🇪🇺 eu
125.0
From 247 benchmarks. Plenty of data behind it.
101 ±7
Coding IQ 101.2, 95% interval 94–108. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.74$2.22164K
63.8
Good value (63.8). Cheaper per task than its benchmark results predict. Plenty of data behind it.
Not measured
146.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
DeepSeek V3.2
🇨🇳
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 versionDeepSeek V4We compared the version names in our catalogue.
us.deepseek.v3.2 · 🇺🇸 us
125.0
From 247 benchmarks. Plenty of data behind it.
101 ±7
Coding IQ 101.2, 95% interval 94–108. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.62batch $0.31$1.85batch $0.925164K
63.8
Good value (63.8). Cheaper per task than its benchmark results predict. Plenty of data behind it.
Not measured
146.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Gemma 4 26B A4B
🇺🇸
Maker headquartered in US, 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.
bedrock_mantle/google.gemma-4-26b-a4b
124.9
From 216 benchmarks. Plenty of data behind it.
102 ±8
Coding IQ 101.7, 95% interval 94–110. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.13batch $0.065$0.40batch $0.20256K
56.4
Good value (56.4). Cheaper per task than its benchmark results predict. A fair amount of data behind it.
50 ±9
Typical (50 ±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.
141.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.3
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
bedrock_mantle/us-gov-west-1/xai.grok-4.3
124.2
From 205 benchmarks. Plenty of data behind it.
101 ±8
Coding IQ 101.2, 95% interval 94–109. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.50cache read $0.24batch $0.75$3.00batch $1.501M
39.3
Poor value (39.3). Costs more 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 default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Claude Sonnet 3.7
🇺🇸
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 the version names in our catalogue.
regional.anthropic.claude-3-7-sonnet-20250219-v1:0 · 20250219 · regional
124.0
From 423 benchmarks. Plenty of data behind it.
94 ±9
Coding IQ 93.6, 95% interval 85–103. 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
39.2
Poor value (39.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
49 ±11
Typical (49 ±11). Generates about as many tokens as models with similar coding results. Measured at high effort. Little data behind it, so treat it as a rough estimate.
141
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 3.7
🇺🇸
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 the version names in our catalogue.
claude-3-7-sonnet
124.0
From 423 benchmarks. Plenty of data behind it.
94 ±9
Coding IQ 93.6, 95% interval 85–103. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.00$15.00Not published by the provider
39.2
Poor value (39.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
49 ±11
Typical (49 ±11). Generates about as many tokens as models with similar coding results. Measured at high effort. Little data behind it, so treat it as a rough estimate.
141
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 3.7
🇺🇸
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 the version names in our catalogue.
eu.anthropic.claude-3-7-sonnet-20250219-v1:0 · 20250219 · 🇪🇺 eu
124.0
From 423 benchmarks. Plenty of data behind it.
94 ±9
Coding IQ 93.6, 95% interval 85–103. 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 $3.75200K
39.2
Poor value (39.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
49 ±11
Typical (49 ±11). Generates about as many tokens as models with similar coding results. Measured at high effort. Little data behind it, so treat it as a rough estimate.
141
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 3.7
🇺🇸
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 the version names in our catalogue.
us.anthropic.claude-3-7-sonnet-20250219-v1:0 · 20250219 · 🇺🇸 us
124.0
From 423 benchmarks. Plenty of data behind it.
94 ±9
Coding IQ 93.6, 95% interval 85–103. 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 $3.75200K
39.2
Poor value (39.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
49 ±11
Typical (49 ±11). Generates about as many tokens as models with similar coding results. Measured at high effort. Little data behind it, so treat it as a rough estimate.
141
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 3.7
🇺🇸
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 the version names in our catalogue.
anthropic.claude-3-7-sonnet-20240620-v1:0 · 20240620
124.0
From 423 benchmarks. Plenty of data behind it.
94 ±9
Coding IQ 93.6, 95% interval 85–103. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.60cache read $0.36$18.00cache write $4.50200K
39.2
Poor value (39.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
49 ±11
Typical (49 ±11). Generates about as many tokens as models with similar coding results. Measured at high effort. Little data behind it, so treat it as a rough estimate.
141
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 3.7
🇺🇸
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 the version names in our catalogue.
anthropic.claude-3-7-sonnet-20250219-v1:0 · 20250219
124.0
From 423 benchmarks. Plenty of data behind it.
94 ±9
Coding IQ 93.6, 95% interval 85–103. 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 $3.75200K
39.2
Poor value (39.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
49 ±11
Typical (49 ±11). Generates about as many tokens as models with similar coding results. Measured at high effort. Little data behind it, so treat it as a rough estimate.
141
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 3.7
🇺🇸
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 the version names in our catalogue.
claude-3-7-sonnet-20250219 · 20250219
124.0
From 423 benchmarks. Plenty of data behind it.
94 ±9
Coding IQ 93.6, 95% interval 85–103. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.00$15.00Not published by the provider
39.2
Poor value (39.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
49 ±11
Typical (49 ±11). Generates about as many tokens as models with similar coding results. Measured at high effort. Little data behind it, so treat it as a rough estimate.
141
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Kimi K2 Thinking
🇨🇳
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.
bedrock_mantle/moonshotai.kimi-k2-thinking
123.8
From 184 benchmarks. Plenty of data behind it.
100 ±6
Coding IQ 100.2, 95% interval 94–106. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.60batch $0.30$2.50batch $1.25256K
41.6
Poor value (41.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
50 ±18
Typical (50 ±18). 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.
145.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
MiniMax M2.5
🇨🇳
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.
minimax.minimax-m2.5
122.8
From 192 benchmarks. Plenty of data behind it.
100 ±6
Coding IQ 100.4, 95% interval 94–106. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.36batch $0.18$1.44batch $0.72196K
48.7
Fair value (48.7). Costs per task about what its benchmark results predict. Plenty of data behind it.
64 ±9
Chatty (64 ±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Claude Haiku 4.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Haiku 5.5We compared release dates and version names in our catalogue.
anthropic.claude-haiku-4-5-20251001-v1:0 · 20251001
122.6
From 470 benchmarks. Plenty of data behind it.
95 ±6
Coding IQ 95.1, 95% interval 90–101. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.00cache read $0.10batch $0.50$5.00cache write $1.25batch $2.50200K
35.0
Poor value (35.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 ±10
Chatty (59 ±10). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
142.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Haiku 4.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Haiku 5.5We compared release dates and version names in our catalogue.
global.anthropic.claude-haiku-4-5-20251001-v1:0 · 20251001 · global
122.6
From 470 benchmarks. Plenty of data behind it.
95 ±6
Coding IQ 95.1, 95% interval 90–101. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.00cache read $0.10batch $0.50$5.00cache write $1.25batch $2.50200K
35.0
Poor value (35.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 ±10
Chatty (59 ±10). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
142.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Haiku 4.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Haiku 5.5We compared release dates and version names in our catalogue.
regional.anthropic.claude-haiku-4-5-20251001-v1:0 · 20251001 · regional
122.6
From 470 benchmarks. Plenty of data behind it.
95 ±6
Coding IQ 95.1, 95% interval 90–101. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.10cache read $0.11$5.50cache write $1.375Not published by the provider
35.0
Poor value (35.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 ±10
Chatty (59 ±10). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
142.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Haiku 4.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Haiku 5.5We compared release dates and version names in our catalogue.
bedrock_mantle/anthropic.claude-haiku-4-5
122.6
From 470 benchmarks. Plenty of data behind it.
95 ±6
Coding IQ 95.1, 95% interval 90–101. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.10cache read $0.11batch $0.55$5.50cache write $1.375batch $2.75200K
35.0
Poor value (35.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 ±10
Chatty (59 ±10). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
142.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Haiku 4.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Haiku 5.5We compared release dates and version names in our catalogue.
anthropic.claude-haiku-4-5@20251001 · 20251001
122.6
From 470 benchmarks. Plenty of data behind it.
95 ±6
Coding IQ 95.1, 95% interval 90–101. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.00cache read $0.10$5.00cache write $1.25200K
35.0
Poor value (35.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 ±10
Chatty (59 ±10). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
142.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Haiku 4.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Haiku 5.5We compared release dates and version names in our catalogue.
apac.anthropic.claude-haiku-4-5-20251001-v1:0 · 20251001 · apac
122.6
From 470 benchmarks. Plenty of data behind it.
95 ±6
Coding IQ 95.1, 95% interval 90–101. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.10cache read $0.11batch $0.55$5.50cache write $1.375batch $2.75200K
35.0
Poor value (35.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 ±10
Chatty (59 ±10). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
142.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Haiku 4.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Haiku 5.5We compared release dates and version names in our catalogue.
au.anthropic.claude-haiku-4-5-20251001-v1:0 · 20251001 · 🇦🇺 au
122.6
From 470 benchmarks. Plenty of data behind it.
95 ±6
Coding IQ 95.1, 95% interval 90–101. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.10cache read $0.11batch $0.55$5.50cache write $1.375batch $2.75200K
35.0
Poor value (35.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 ±10
Chatty (59 ±10). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
142.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Haiku 4.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Haiku 5.5We compared release dates and version names in our catalogue.
eu.anthropic.claude-haiku-4-5-20251001-v1:0 · 20251001 · 🇪🇺 eu
122.6
From 470 benchmarks. Plenty of data behind it.
95 ±6
Coding IQ 95.1, 95% interval 90–101. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.10cache read $0.11batch $0.55$5.50cache write $1.375batch $2.75200K
35.0
Poor value (35.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 ±10
Chatty (59 ±10). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
142.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Haiku 4.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Haiku 5.5We compared release dates and version names in our catalogue.
jp.anthropic.claude-haiku-4-5-20251001-v1:0 · 20251001 · 🇯🇵 jp
122.6
From 470 benchmarks. Plenty of data behind it.
95 ±6
Coding IQ 95.1, 95% interval 90–101. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.10cache read $0.11batch $0.55$5.50cache write $1.375batch $2.75200K
35.0
Poor value (35.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 ±10
Chatty (59 ±10). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
142.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Haiku 4.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Haiku 5.5We compared release dates and version names in our catalogue.
us.anthropic.claude-haiku-4-5-20251001-v1:0 · 20251001 · 🇺🇸 us
122.6
From 470 benchmarks. Plenty of data behind it.
95 ±6
Coding IQ 95.1, 95% interval 90–101. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.10cache read $0.11batch $0.55$5.50cache write $1.375batch $2.75200K
35.0
Poor value (35.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 ±10
Chatty (59 ±10). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
142.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Haiku 4.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Haiku 5.5We compared release dates and version names in our catalogue.
claude-haiku-4-5-20251001 · 20251001
122.6
From 470 benchmarks. Plenty of data behind it.
95 ±6
Coding IQ 95.1, 95% interval 90–101. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.00$5.00Not published by the provider
35.0
Poor value (35.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 ±10
Chatty (59 ±10). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
142.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
MiniMax M2.1
🇨🇳
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.
minimax.minimax-m2.1
122.3
From 97 benchmarks. Plenty of data behind it.
97 ±6
Coding IQ 96.5, 95% interval 91–102. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.30batch $0.15$1.20batch $0.60196K
45.1
Poor value (45.1). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 ±13
Chatty (59 ±13). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
DeepSeek R1
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
us.deepseek.r1-v1:0 · 🇺🇸 us
121.9
From 412 benchmarks. Plenty of data behind it.
93 ±14
Coding IQ 92.9, 95% interval 79–107. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.35$5.40128K
36.1
Poor value (36.1). Costs more per task than its benchmark results predict. Plenty of data behind it.
60 ±11
Chatty (60 ±11). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
140.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Qwen3 235B A22B Instruct 2507
🇨🇳
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.
bedrock_mantle/qwen.qwen3-235b-a22b-2507
120.7
From 258 benchmarks. Plenty of data behind it.
92 ±11
Coding IQ 92.4, 95% interval 82–103. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.22batch $0.11$0.88batch $0.44256K
58.8
Good value (58.8). Cheaper per task than its benchmark results predict. Plenty of data behind it.
Not measured
138
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Qwen3 235B A22B Instruct 2507
🇨🇳
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.
qwen.qwen3-235b-a22b-2507-v1:0
120.7
From 258 benchmarks. Plenty of data behind it.
92 ±11
Coding IQ 92.4, 95% interval 82–103. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.22batch $0.11$0.88batch $0.44262K
58.8
Good value (58.8). Cheaper per task than its benchmark results predict. Plenty of data behind it.
Not measured
138
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Qwen3 VL 235B
🇨🇳
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.
qwen.qwen3-vl-235b-a22b
120.4
From 170 benchmarks. Plenty of data behind it.
≈ 94 ±18
Coding IQ 94.2, 95% interval 76–113. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.53batch $0.26$2.66batch $1.33256K
45.0
Poor value (45.0). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measuredNot measured
Qwen3 VL 235B
🇨🇳
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.
qwen.qwen3-vl-235b-a22b-v1:0
120.4
From 170 benchmarks. Plenty of data behind it.
≈ 94 ±18
Coding IQ 94.2, 95% interval 76–113. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.53$2.66Not published by the provider
45.0
Poor value (45.0). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measuredNot measured
Qwen3 Next 80B A3B
🇨🇳
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.
qwen.qwen3-next-80b-a3b
120.2
From 191 benchmarks. Plenty of data behind it.
90 ±12
Coding IQ 90.0, 95% interval 78–102. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.18batch $0.09$1.41batch $0.71262K
51.1
Fair value (51.1). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured

Run by Amazon Web Services

75 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
GPT-6 Luna
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
global
 OpenRouter
135.6
From 227 benchmarks. Plenty of data behind it.
117 ±6
Coding IQ 116.9, 95% interval 111–123. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.10cache read $0.01$0.50cache write $0.125922K
63.4
Good value (63.4). 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.
156.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-5.6 Luna
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-6 LunaWe compared release dates and version names in our catalogue.
global
 OpenRouter
135.2
From 344 benchmarks. Plenty of data behind it.
112 ±10
Coding IQ 112.4, 95% interval 102–123. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.20cache read $0.02$1.20cache write $0.25922K
66.2
Good value (66.2). Cheaper per task than its benchmark results predict. Plenty of data behind it.
52 ±8
Typical (52 ±8). Generates about as many tokens as models with similar coding results. Measured at max effort. A fair amount of data behind it.
156.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Haiku 5.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
 Cortecs AI
134.6
From 230 benchmarks. Plenty of data behind it.
124 ±6
Coding IQ 123.6, 95% interval 118–129. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
——1M
62.1
Good value (62.1). Cheaper per task than its benchmark results predict. Plenty of data behind it.
49 ±9
Typical (49 ±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.
160.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Haiku 5.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
anthropic.claude-haiku-5-5
 Llmgateway
134.6
From 230 benchmarks. Plenty of data behind it.
124 ±6
Coding IQ 123.6, 95% interval 118–129. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.10cache read $0.01$0.50cache write $0.125Not published by the provider
62.1
Good value (62.1). Cheaper per task than its benchmark results predict. Plenty of data behind it.
49 ±9
Typical (49 ±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.
160.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Haiku 5.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
 OpenRouter
134.6
From 230 benchmarks. Plenty of data behind it.
124 ±6
Coding IQ 123.6, 95% interval 118–129. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.10cache read $0.01$0.50cache write $0.1251M
62.1
Good value (62.1). Cheaper per task than its benchmark results predict. Plenty of data behind it.
49 ±9
Typical (49 ±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.
160.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.5
🇺🇸
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
134.0
From 384 benchmarks. Plenty of data behind it.
113 ±5
Coding IQ 112.8, 95% interval 108–118. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
——200K
46.0
Poor value (46.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
43 ±10
Terse (43 ±10). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
151.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.5
🇺🇸
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-4-5-20251101-v1:0 · 20251101
 Llmgateway
134.0
From 384 benchmarks. Plenty of data behind it.
113 ±5
Coding IQ 112.8, 95% interval 108–118. 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
46.0
Poor value (46.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
43 ±10
Terse (43 ±10). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
151.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.5
🇺🇸
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
134.0
From 384 benchmarks. Plenty of data behind it.
113 ±5
Coding IQ 112.8, 95% interval 108–118. 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 $6.25200K
46.0
Poor value (46.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
43 ±10
Terse (43 ±10). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
151.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.5
🇺🇸
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
134.0
From 384 benchmarks. Plenty of data behind it.
113 ±5
Coding IQ 112.8, 95% interval 108–118. 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 $6.25200K
46.0
Poor value (46.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
43 ±10
Terse (43 ±10). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
151.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.5
🇺🇸
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-4-5@eu-central-1 · 🇩🇪 eu-central-1
 Requesty
134.0
From 384 benchmarks. Plenty of data behind it.
113 ±5
Coding IQ 112.8, 95% interval 108–118. 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 $6.875200K
46.0
Poor value (46.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
43 ±10
Terse (43 ±10). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
151.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.5
🇺🇸
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-4-5@eu-north-1 · 🇸🇪 eu-north-1
 Requesty
134.0
From 384 benchmarks. Plenty of data behind it.
113 ±5
Coding IQ 112.8, 95% interval 108–118. 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 $6.875200K
46.0
Poor value (46.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
43 ±10
Terse (43 ±10). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
151.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.5
🇺🇸
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-4-5@eu-west-1 · 🇮🇪 eu-west-1
 Requesty
134.0
From 384 benchmarks. Plenty of data behind it.
113 ±5
Coding IQ 112.8, 95% interval 108–118. 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 $6.875200K
46.0
Poor value (46.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
43 ±10
Terse (43 ±10). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
151.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.5
🇺🇸
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-4-5@eu-west-3 · 🇫🇷 eu-west-3
 Requesty
134.0
From 384 benchmarks. Plenty of data behind it.
113 ±5
Coding IQ 112.8, 95% interval 108–118. 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 $6.875200K
46.0
Poor value (46.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
43 ±10
Terse (43 ±10). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
151.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.5
🇺🇸
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-4-5@us-east-1 · 🇺🇸 us-east-1
 Requesty
134.0
From 384 benchmarks. Plenty of data behind it.
113 ±5
Coding IQ 112.8, 95% interval 108–118. 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 $6.875200K
46.0
Poor value (46.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
43 ±10
Terse (43 ±10). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
151.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.5
🇺🇸
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-4-5@us-east-2 · 🇺🇸 us-east-2
 Requesty
134.0
From 384 benchmarks. Plenty of data behind it.
113 ±5
Coding IQ 112.8, 95% interval 108–118. 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 $6.875200K
46.0
Poor value (46.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
43 ±10
Terse (43 ±10). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
151.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.5
🇺🇸
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-4-5@us-west-2 · 🇺🇸 us-west-2
 Requesty
134.0
From 384 benchmarks. Plenty of data behind it.
113 ±5
Coding IQ 112.8, 95% interval 108–118. 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 $6.875200K
46.0
Poor value (46.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
43 ±10
Terse (43 ±10). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
151.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.6
🇺🇸
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.
claude-4-6-sonnet
 Cortecs AI
133.8
From 469 benchmarks. Plenty of data behind it.
108 ±6
Coding IQ 108.4, 95% interval 103–114. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
——1M
35.4
Poor value (35.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
71 ±8
Chatty (71 ±8). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
152.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.6
🇺🇸
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-4-6
 Llmgateway
133.8
From 469 benchmarks. Plenty of data behind it.
108 ±6
Coding IQ 108.4, 95% interval 103–114. 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
35.4
Poor value (35.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
71 ±8
Chatty (71 ±8). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
152.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.6
🇺🇸
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
133.8
From 469 benchmarks. Plenty of data behind it.
108 ±6
Coding IQ 108.4, 95% interval 103–114. 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
35.4
Poor value (35.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
71 ±8
Chatty (71 ±8). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
152.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.6
🇺🇸
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
133.8
From 469 benchmarks. Plenty of data behind it.
108 ±6
Coding IQ 108.4, 95% interval 103–114. 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
35.4
Poor value (35.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
71 ±8
Chatty (71 ±8). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
152.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.6
🇺🇸
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-4-6@ap-northeast-1 · 🇯🇵 ap-northeast-1
 Requesty
133.8
From 469 benchmarks. Plenty of data behind it.
108 ±6
Coding IQ 108.4, 95% interval 103–114. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.30cache read $0.30$16.50cache write $4.1251M
35.4
Poor value (35.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
71 ±8
Chatty (71 ±8). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
152.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.6
🇺🇸
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-4-6@eu-central-1 · 🇩🇪 eu-central-1
 Requesty
133.8
From 469 benchmarks. Plenty of data behind it.
108 ±6
Coding IQ 108.4, 95% interval 103–114. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.30cache read $0.30$16.50cache write $4.1251M
35.4
Poor value (35.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
71 ±8
Chatty (71 ±8). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
152.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.6
🇺🇸
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-4-6@eu-north-1 · 🇸🇪 eu-north-1
 Requesty
133.8
From 469 benchmarks. Plenty of data behind it.
108 ±6
Coding IQ 108.4, 95% interval 103–114. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.30cache read $0.30$16.50cache write $4.1251M
35.4
Poor value (35.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
71 ±8
Chatty (71 ±8). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
152.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.6
🇺🇸
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-4-6@eu-west-1 · 🇮🇪 eu-west-1
 Requesty
133.8
From 469 benchmarks. Plenty of data behind it.
108 ±6
Coding IQ 108.4, 95% interval 103–114. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.30cache read $0.30$16.50cache write $4.1251M
35.4
Poor value (35.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
71 ±8
Chatty (71 ±8). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
152.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.6
🇺🇸
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-4-6@eu-west-3 · 🇫🇷 eu-west-3
 Requesty
133.8
From 469 benchmarks. Plenty of data behind it.
108 ±6
Coding IQ 108.4, 95% interval 103–114. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.30cache read $0.30$16.50cache write $4.1251M
35.4
Poor value (35.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
71 ±8
Chatty (71 ±8). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
152.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.6
🇺🇸
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-4-6@us-east-1 · 🇺🇸 us-east-1
 Requesty
133.8
From 469 benchmarks. Plenty of data behind it.
108 ±6
Coding IQ 108.4, 95% interval 103–114. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.30cache read $0.30$16.50cache write $4.1251M
35.4
Poor value (35.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
71 ±8
Chatty (71 ±8). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
152.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.6
🇺🇸
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-4-6@us-east-2 · 🇺🇸 us-east-2
 Requesty
133.8
From 469 benchmarks. Plenty of data behind it.
108 ±6
Coding IQ 108.4, 95% interval 103–114. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.30cache read $0.30$16.50cache write $4.1251M
35.4
Poor value (35.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
71 ±8
Chatty (71 ±8). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
152.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.6
🇺🇸
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-4-6@us-west-2 · 🇺🇸 us-west-2
 Requesty
133.8
From 469 benchmarks. Plenty of data behind it.
108 ±6
Coding IQ 108.4, 95% interval 103–114. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.30cache read $0.30$16.50cache write $4.1251M
35.4
Poor value (35.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
71 ±8
Chatty (71 ±8). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
152.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.5
🇺🇸
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.
claude-4-5-sonnet
 Cortecs AI
129.7
From 442 benchmarks. Plenty of data behind it.
107 ±7
Coding IQ 107.2, 95% interval 101–114. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
——200K
40.2
Poor value (40.2). Costs more 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 default effort. A fair amount of data behind it.
147.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.5
🇺🇸
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-4-5-20250929-v1:0
 Llmgateway
129.7
From 442 benchmarks. Plenty of data behind it.
107 ±7
Coding IQ 107.2, 95% interval 101–114. 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
40.2
Poor value (40.2). Costs more 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 default effort. A fair amount of data behind it.
147.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.5
🇺🇸
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-4-5-20250929-v1:0 · 20250929
 Llmgateway
129.7
From 442 benchmarks. Plenty of data behind it.
107 ±7
Coding IQ 107.2, 95% interval 101–114. 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
40.2
Poor value (40.2). Costs more 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 default effort. A fair amount of data behind it.
147.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.5
🇺🇸
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.
 OpenRouter
129.7
From 442 benchmarks. Plenty of data behind it.
107 ±7
Coding IQ 107.2, 95% interval 101–114. 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
40.2
Poor value (40.2). Costs more 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 default effort. A fair amount of data behind it.
147.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.5
🇺🇸
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
129.7
From 442 benchmarks. Plenty of data behind it.
107 ±7
Coding IQ 107.2, 95% interval 101–114. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.00>200k $6.00cache read $0.30$15.00>200k $22.50cache write $3.751M
40.2
Poor value (40.2). Costs more 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 default effort. A fair amount of data behind it.
147.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.5
🇺🇸
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-4-5@eu-central-1 · 🇩🇪 eu-central-1
 Requesty
129.7
From 442 benchmarks. Plenty of data behind it.
107 ±7
Coding IQ 107.2, 95% interval 101–114. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.30>200k $6.60cache read $0.30$16.50>200k $24.75cache write $4.1251M
40.2
Poor value (40.2). Costs more 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 default effort. A fair amount of data behind it.
147.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.5
🇺🇸
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-4-5@eu-north-1 · 🇸🇪 eu-north-1
 Requesty
129.7
From 442 benchmarks. Plenty of data behind it.
107 ±7
Coding IQ 107.2, 95% interval 101–114. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.30>200k $6.60cache read $0.30$16.50>200k $24.75cache write $4.1251M
40.2
Poor value (40.2). Costs more 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 default effort. A fair amount of data behind it.
147.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.5
🇺🇸
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-4-5@eu-west-1 · 🇮🇪 eu-west-1
 Requesty
129.7
From 442 benchmarks. Plenty of data behind it.
107 ±7
Coding IQ 107.2, 95% interval 101–114. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.30>200k $6.60cache read $0.30$16.50>200k $24.75cache write $4.1251M
40.2
Poor value (40.2). Costs more 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 default effort. A fair amount of data behind it.
147.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.5
🇺🇸
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-4-5@eu-west-3 · 🇫🇷 eu-west-3
 Requesty
129.7
From 442 benchmarks. Plenty of data behind it.
107 ±7
Coding IQ 107.2, 95% interval 101–114. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.30>200k $6.60cache read $0.30$16.50>200k $24.75cache write $4.1251M
40.2
Poor value (40.2). Costs more 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 default effort. A fair amount of data behind it.
147.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.5
🇺🇸
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-4-5@us-east-1 · 🇺🇸 us-east-1
 Requesty
129.7
From 442 benchmarks. Plenty of data behind it.
107 ±7
Coding IQ 107.2, 95% interval 101–114. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.30>200k $6.60cache read $0.30$16.50>200k $24.75cache write $4.1251M
40.2
Poor value (40.2). Costs more 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 default effort. A fair amount of data behind it.
147.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.5
🇺🇸
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-4-5@us-east-2 · 🇺🇸 us-east-2
 Requesty
129.7
From 442 benchmarks. Plenty of data behind it.
107 ±7
Coding IQ 107.2, 95% interval 101–114. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.30>200k $6.60cache read $0.30$16.50>200k $24.75cache write $4.1251M
40.2
Poor value (40.2). Costs more 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 default effort. A fair amount of data behind it.
147.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.5
🇺🇸
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-4-5@us-west-2 · 🇺🇸 us-west-2
 Requesty
129.7
From 442 benchmarks. Plenty of data behind it.
107 ±7
Coding IQ 107.2, 95% interval 101–114. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.30>200k $6.60cache read $0.30$16.50>200k $24.75cache write $4.1251M
40.2
Poor value (40.2). Costs more 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 default effort. A fair amount of data behind it.
147.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGLM 5.3We compared release dates and version names in our catalogue.
 Hugging Face
129.7
From 306 benchmarks. Plenty of data behind it.
107 ±5
Coding IQ 106.7, 95% interval 102–112. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.00$3.20203K
49.7
Fair value (49.7). Costs per task about what 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 default effort. Little data behind it, so treat it as a rough estimate.
146.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGLM 5.3We compared release dates and version names in our catalogue.
 OpenRouter
129.7
From 306 benchmarks. Plenty of data behind it.
107 ±5
Coding IQ 106.7, 95% interval 102–112. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.00$3.20203K
49.7
Fair value (49.7). Costs per task about what 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 default effort. Little data behind it, so treat it as a rough estimate.
146.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Kimi K2.5
🇨🇳
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.
amazon/moonshotai.kimi-k2.5
 Eden AI
128.5
From 401 benchmarks. Plenty of data behind it.
103 ±5
Coding IQ 102.9, 95% interval 98–108. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.60$3.00262K
48.2
Fair value (48.2). Costs per task about what its benchmark results predict. Plenty of data behind it.
42 ±9
Terse (42 ±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.
148.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Kimi K2.5
🇨🇳
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
128.5
From 401 benchmarks. Plenty of data behind it.
103 ±5
Coding IQ 102.9, 95% interval 98–108. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.60$3.00262K
48.2
Fair value (48.2). Costs per task about what its benchmark results predict. Plenty of data behind it.
42 ±9
Terse (42 ±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.
148.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Kimi K2.5
🇨🇳
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
128.5
From 401 benchmarks. Plenty of data behind it.
103 ±5
Coding IQ 102.9, 95% interval 98–108. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.60$3.00262K
48.2
Fair value (48.2). Costs per task about what its benchmark results predict. Plenty of data behind it.
42 ±9
Terse (42 ±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.
148.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Kimi K2.5
🇨🇳
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.
bedrock/kimi-k2.5@eu-north-1 · 🇸🇪 eu-north-1
 Requesty
128.5
From 401 benchmarks. Plenty of data behind it.
103 ±5
Coding IQ 102.9, 95% interval 98–108. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.72$3.60cache write $0.72128K
48.2
Fair value (48.2). Costs per task about what its benchmark results predict. Plenty of data behind it.
42 ±9
Terse (42 ±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.
148.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Kimi K2.5
🇨🇳
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.
bedrock/kimi-k2.5@eu-west-2 · 🇬🇧 eu-west-2
 Requesty
128.5
From 401 benchmarks. Plenty of data behind it.
103 ±5
Coding IQ 102.9, 95% interval 98–108. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.72$3.60cache write $0.72128K
48.2
Fair value (48.2). Costs per task about what its benchmark results predict. Plenty of data behind it.
42 ±9
Terse (42 ±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.
148.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Kimi K2.5
🇨🇳
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.
bedrock/kimi-k2.5@us-east-1 · 🇺🇸 us-east-1
 Requesty
128.5
From 401 benchmarks. Plenty of data behind it.
103 ±5
Coding IQ 102.9, 95% interval 98–108. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.60$3.00128K
48.2
Fair value (48.2). Costs per task about what its benchmark results predict. Plenty of data behind it.
42 ±9
Terse (42 ±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.
148.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Kimi K2.5
🇨🇳
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.
bedrock/kimi-k2.5@us-east-2 · 🇺🇸 us-east-2
 Requesty
128.5
From 401 benchmarks. Plenty of data behind it.
103 ±5
Coding IQ 102.9, 95% interval 98–108. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.60$3.00128K
48.2
Fair value (48.2). Costs per task about what its benchmark results predict. Plenty of data behind it.
42 ±9
Terse (42 ±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.
148.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Kimi K2.5
🇨🇳
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.
bedrock/kimi-k2.5@us-west-2 · 🇺🇸 us-west-2
 Requesty
128.5
From 401 benchmarks. Plenty of data behind it.
103 ±5
Coding IQ 102.9, 95% interval 98–108. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.60$3.00128K
48.2
Fair value (48.2). Costs per task about what its benchmark results predict. Plenty of data behind it.
42 ±9
Terse (42 ±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.
148.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Opus 4.1
🇺🇸
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
128.3
From 249 benchmarks. Plenty of data behind it.
109 ±7
Coding IQ 108.6, 95% interval 102–115. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$15.00cache read $1.50$75.00cache write $18.75200K
34.6
Poor value (34.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
35 ±9
Terse (35 ±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.
144.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.3
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
xai.grok-4.3
 Llmgateway
124.2
From 205 benchmarks. Plenty of data behind it.
101 ±8
Coding IQ 101.2, 95% interval 94–109. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.25cache read $0.20$2.50Not published by the provider
39.3
Poor value (39.3). Costs more 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 default effort. Little data behind it, so treat it as a rough estimate.
Not measured
MiniMax M2.5
🇨🇳
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.
 Cortecs AI
122.8
From 192 benchmarks. Plenty of data behind it.
100 ±6
Coding IQ 100.4, 95% interval 94–106. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
——196K
48.7
Fair value (48.7). Costs per task about what its benchmark results predict. Plenty of data behind it.
64 ±9
Chatty (64 ±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
MiniMax M2.5
🇨🇳
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.
bedrock/minimax-m2.5@eu-central-1 · 🇩🇪 eu-central-1
 Requesty
122.8
From 192 benchmarks. Plenty of data behind it.
100 ±6
Coding IQ 100.4, 95% interval 94–106. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.36$1.44128K
48.7
Fair value (48.7). Costs per task about what its benchmark results predict. Plenty of data behind it.
64 ±9
Chatty (64 ±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
MiniMax M2.5
🇨🇳
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.
bedrock/minimax-m2.5@eu-north-1 · 🇸🇪 eu-north-1
 Requesty
122.8
From 192 benchmarks. Plenty of data behind it.
100 ±6
Coding IQ 100.4, 95% interval 94–106. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.36$1.44128K
48.7
Fair value (48.7). Costs per task about what its benchmark results predict. Plenty of data behind it.
64 ±9
Chatty (64 ±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
MiniMax M2.5
🇨🇳
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.
bedrock/minimax-m2.5@eu-south-1 · 🇮🇹 eu-south-1
 Requesty
122.8
From 192 benchmarks. Plenty of data behind it.
100 ±6
Coding IQ 100.4, 95% interval 94–106. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.36$1.44128K
48.7
Fair value (48.7). Costs per task about what its benchmark results predict. Plenty of data behind it.
64 ±9
Chatty (64 ±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
MiniMax M2.5
🇨🇳
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.
bedrock/minimax-m2.5@eu-west-1 · 🇮🇪 eu-west-1
 Requesty
122.8
From 192 benchmarks. Plenty of data behind it.
100 ±6
Coding IQ 100.4, 95% interval 94–106. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.36$1.44128K
48.7
Fair value (48.7). Costs per task about what its benchmark results predict. Plenty of data behind it.
64 ±9
Chatty (64 ±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
MiniMax M2.5
🇨🇳
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.
bedrock/minimax-m2.5@us-east-1 · 🇺🇸 us-east-1
 Requesty
122.8
From 192 benchmarks. Plenty of data behind it.
100 ±6
Coding IQ 100.4, 95% interval 94–106. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.30$1.20128K
48.7
Fair value (48.7). Costs per task about what its benchmark results predict. Plenty of data behind it.
64 ±9
Chatty (64 ±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
MiniMax M2.5
🇨🇳
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.
bedrock/minimax-m2.5@us-east-2 · 🇺🇸 us-east-2
 Requesty
122.8
From 192 benchmarks. Plenty of data behind it.
100 ±6
Coding IQ 100.4, 95% interval 94–106. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.30$1.20128K
48.7
Fair value (48.7). Costs per task about what its benchmark results predict. Plenty of data behind it.
64 ±9
Chatty (64 ±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
MiniMax M2.5
🇨🇳
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.
bedrock/minimax-m2.5@us-west-2 · 🇺🇸 us-west-2
 Requesty
122.8
From 192 benchmarks. Plenty of data behind it.
100 ±6
Coding IQ 100.4, 95% interval 94–106. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.30$1.20128K
48.7
Fair value (48.7). Costs per task about what its benchmark results predict. Plenty of data behind it.
64 ±9
Chatty (64 ±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Claude Haiku 4.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Haiku 5.5We compared release dates and version names in our catalogue.
 Cortecs AI
122.6
From 470 benchmarks. Plenty of data behind it.
95 ±6
Coding IQ 95.1, 95% interval 90–101. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
——200K
35.0
Poor value (35.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 ±10
Chatty (59 ±10). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
142.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Haiku 4.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Haiku 5.5We compared release dates and version names in our catalogue.
anthropic.claude-haiku-4-5-20251001-v1:0
 Llmgateway
122.6
From 470 benchmarks. Plenty of data behind it.
95 ±6
Coding IQ 95.1, 95% interval 90–101. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.00cache read $0.10$5.00cache write $1.25Not published by the provider
35.0
Poor value (35.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 ±10
Chatty (59 ±10). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
142.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Haiku 4.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Haiku 5.5We compared release dates and version names in our catalogue.
anthropic.claude-haiku-4-5-20251001-v1:0 · 20251001
 Llmgateway
122.6
From 470 benchmarks. Plenty of data behind it.
95 ±6
Coding IQ 95.1, 95% interval 90–101. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.00cache read $0.10$5.00cache write $1.25Not published by the provider
35.0
Poor value (35.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 ±10
Chatty (59 ±10). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
142.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Haiku 4.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Haiku 5.5We compared release dates and version names in our catalogue.
global
 OpenRouter
122.6
From 470 benchmarks. Plenty of data behind it.
95 ±6
Coding IQ 95.1, 95% interval 90–101. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.00cache read $0.10$5.00cache write $1.25200K
35.0
Poor value (35.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 ±10
Chatty (59 ±10). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
142.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Haiku 4.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Haiku 5.5We compared release dates and version names in our catalogue.
 Requesty
122.6
From 470 benchmarks. Plenty of data behind it.
95 ±6
Coding IQ 95.1, 95% interval 90–101. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.00cache read $0.10$5.00cache write $1.25200K
35.0
Poor value (35.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 ±10
Chatty (59 ±10). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
142.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Haiku 4.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Haiku 5.5We compared release dates and version names in our catalogue.
bedrock/claude-haiku-4-5@ap-northeast-1 · 🇯🇵 ap-northeast-1
 Requesty
122.6
From 470 benchmarks. Plenty of data behind it.
95 ±6
Coding IQ 95.1, 95% interval 90–101. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.10cache read $0.11$5.50cache write $1.375200K
35.0
Poor value (35.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 ±10
Chatty (59 ±10). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
142.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Haiku 4.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Haiku 5.5We compared release dates and version names in our catalogue.
bedrock/claude-haiku-4-5@eu-central-1 · 🇩🇪 eu-central-1
 Requesty
122.6
From 470 benchmarks. Plenty of data behind it.
95 ±6
Coding IQ 95.1, 95% interval 90–101. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.10cache read $0.11$5.50cache write $1.375200K
35.0
Poor value (35.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 ±10
Chatty (59 ±10). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
142.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Haiku 4.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Haiku 5.5We compared release dates and version names in our catalogue.
bedrock/claude-haiku-4-5@eu-north-1 · 🇸🇪 eu-north-1
 Requesty
122.6
From 470 benchmarks. Plenty of data behind it.
95 ±6
Coding IQ 95.1, 95% interval 90–101. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.10cache read $0.11$5.50cache write $1.375200K
35.0
Poor value (35.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 ±10
Chatty (59 ±10). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
142.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Haiku 4.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Haiku 5.5We compared release dates and version names in our catalogue.
bedrock/claude-haiku-4-5@eu-west-1 · 🇮🇪 eu-west-1
 Requesty
122.6
From 470 benchmarks. Plenty of data behind it.
95 ±6
Coding IQ 95.1, 95% interval 90–101. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.10cache read $0.11$5.50cache write $1.375200K
35.0
Poor value (35.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 ±10
Chatty (59 ±10). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
142.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Haiku 4.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Haiku 5.5We compared release dates and version names in our catalogue.
bedrock/claude-haiku-4-5@eu-west-3 · 🇫🇷 eu-west-3
 Requesty
122.6
From 470 benchmarks. Plenty of data behind it.
95 ±6
Coding IQ 95.1, 95% interval 90–101. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.10cache read $0.11$5.50cache write $1.375200K
35.0
Poor value (35.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 ±10
Chatty (59 ±10). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
142.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Haiku 4.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Haiku 5.5We compared release dates and version names in our catalogue.
bedrock/claude-haiku-4-5@us-east-1 · 🇺🇸 us-east-1
 Requesty
122.6
From 470 benchmarks. Plenty of data behind it.
95 ±6
Coding IQ 95.1, 95% interval 90–101. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.10cache read $0.11$5.50cache write $1.375200K
35.0
Poor value (35.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 ±10
Chatty (59 ±10). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
142.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Haiku 4.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Haiku 5.5We compared release dates and version names in our catalogue.
bedrock/claude-haiku-4-5@us-east-2 · 🇺🇸 us-east-2
 Requesty
122.6
From 470 benchmarks. Plenty of data behind it.
95 ±6
Coding IQ 95.1, 95% interval 90–101. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.10cache read $0.11$5.50cache write $1.375200K
35.0
Poor value (35.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 ±10
Chatty (59 ±10). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
142.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Haiku 4.5
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Haiku 5.5We compared release dates and version names in our catalogue.
bedrock/claude-haiku-4-5@us-west-2 · 🇺🇸 us-west-2
 Requesty
122.6
From 470 benchmarks. Plenty of data behind it.
95 ±6
Coding IQ 95.1, 95% interval 90–101. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.10cache read $0.11$5.50cache write $1.375200K
35.0
Poor value (35.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 ±10
Chatty (59 ±10). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
142.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
MiniMax M2.1
🇨🇳
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.
 Cortecs AI
122.3
From 97 benchmarks. Plenty of data behind it.
97 ±6
Coding IQ 96.5, 95% interval 91–102. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
——196K
45.1
Poor value (45.1). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 ±13
Chatty (59 ±13). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Qwen3 VL 235B
🇨🇳
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.
qwen3-vl-235b-a22b
 Cortecs AI
120.4
From 170 benchmarks. Plenty of data behind it.
≈ 94 ±18
Coding IQ 94.2, 95% interval 76–113. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
——256K
45.0
Poor value (45.0). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measuredNot measured

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

How this data works