Skip to content

Listings

All listings: OpenRouter

Every listing for the models on page 3 of 26 of OpenRouter, including each model's other versions and routes. Back to OpenRouter

Sold by OpenRouter

231 listings on this page sold by OpenRouter.

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
Muse Spark Open
🇺🇸
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.
136.3
From 58 benchmarks. Plenty of data behind it.
114 ±8
Coding IQ 113.5, 95% interval 105–122. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.25cache read $0.15$4.251M
49.6
Fair value (49.6). Costs per task about what its benchmark results predict. Plenty of data behind it.
Not measured
155.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Muse Spark Open
🇺🇸
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.
fp4
Inference by Baseten
136.3
From 58 benchmarks. Plenty of data behind it.
114 ±8
Coding IQ 113.5, 95% interval 105–122. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.25cache read $0.15$4.251M
49.6
Fair value (49.6). Costs per task about what its benchmark results predict. Plenty of data behind it.
Not measured
155.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Muse Spark Open
🇺🇸
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.
Inference by Fireworks AI
136.3
From 58 benchmarks. Plenty of data behind it.
114 ±8
Coding IQ 113.5, 95% interval 105–122. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.25cache read $0.15$4.251M
49.6
Fair value (49.6). Costs per task about what its benchmark results predict. Plenty of data behind it.
Not measured
155.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Muse Spark Open
🇺🇸
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.
Inference by Modal
136.3
From 58 benchmarks. Plenty of data behind it.
114 ±8
Coding IQ 113.5, 95% interval 105–122. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.25cache read $0.15$4.251M
49.6
Fair value (49.6). Costs per task about what its benchmark results predict. Plenty of data behind it.
Not measured
155.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Muse Spark Open
🇺🇸
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.
fp4
Inference by Nebius AI Studio
136.3
From 58 benchmarks. Plenty of data behind it.
114 ±8
Coding IQ 113.5, 95% interval 105–122. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.25cache read $0.15$4.251M
49.6
Fair value (49.6). Costs per task about what its benchmark results predict. Plenty of data behind it.
Not measured
155.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Muse Spark Open
🇺🇸
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.
Inference by Together AI
136.3
From 58 benchmarks. Plenty of data behind it.
114 ±8
Coding IQ 113.5, 95% interval 105–122. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.25cache read $0.15$4.251M
49.6
Fair value (49.6). Costs per task about what its benchmark results predict. Plenty of data behind it.
Not measured
155.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Gemini 3.1 Pro Preview
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
136.0
From 595 benchmarks. Plenty of data behind it.
110 ±9
Coding IQ 110.0, 95% interval 102–119. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.20$12.001M
49.8
Fair value (49.8). Costs per task about what its benchmark results predict. Plenty of data behind it.
38 ±12
Terse (38 ±12). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
156.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Gemini 3.1 Pro Preview
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
google/gemini-3.1-pro-preview:batch · batch
136.0
From 595 benchmarks. Plenty of data behind it.
110 ±9
Coding IQ 110.0, 95% interval 102–119. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.00$6.001M
49.8
Fair value (49.8). Costs per task about what its benchmark results predict. Plenty of data behind it.
38 ±12
Terse (38 ±12). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
156.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Gemini 3.1 Pro Preview
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
google/gemini-3.1-pro-preview-customtools · customtools
136.0
From 595 benchmarks. Plenty of data behind it.
110 ±9
Coding IQ 110.0, 95% interval 102–119. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.20$12.001M
49.8
Fair value (49.8). Costs per task about what its benchmark results predict. Plenty of data behind it.
38 ±12
Terse (38 ±12). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
156.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Gemini 3.1 Pro Preview
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Inference by Google
136.0
From 595 benchmarks. Plenty of data behind it.
110 ±9
Coding IQ 110.0, 95% interval 102–119. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.20$12.001M
49.8
Fair value (49.8). Costs per task about what its benchmark results predict. Plenty of data behind it.
38 ±12
Terse (38 ±12). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
156.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Gemini 3.1 Pro Preview
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
google/gemini-3.1-pro-preview:batch · batch+global
Inference by Google
136.0
From 595 benchmarks. Plenty of data behind it.
110 ±9
Coding IQ 110.0, 95% interval 102–119. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.00$6.001M
49.8
Fair value (49.8). Costs per task about what its benchmark results predict. Plenty of data behind it.
38 ±12
Terse (38 ±12). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
156.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Gemini 3.1 Pro Preview
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
google/gemini-3.1-pro-preview-customtools · customtools
Inference by Google
136.0
From 595 benchmarks. Plenty of data behind it.
110 ±9
Coding IQ 110.0, 95% interval 102–119. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.20$12.001M
49.8
Fair value (49.8). Costs per task about what its benchmark results predict. Plenty of data behind it.
38 ±12
Terse (38 ±12). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
156.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Gemini 3.1 Pro Preview
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
global
Inference by Google
136.0
From 595 benchmarks. Plenty of data behind it.
110 ±9
Coding IQ 110.0, 95% interval 102–119. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.20$12.001M
49.8
Fair value (49.8). Costs per task about what its benchmark results predict. Plenty of data behind it.
38 ±12
Terse (38 ±12). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
156.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Gemini 3.1 Pro Preview
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
global/flex
Inference by Google
136.0
From 595 benchmarks. Plenty of data behind it.
110 ±9
Coding IQ 110.0, 95% interval 102–119. 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$6.001M
49.8
Fair value (49.8). Costs per task about what its benchmark results predict. Plenty of data behind it.
38 ±12
Terse (38 ±12). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
156.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Gemini 3.1 Pro Preview
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
global/priority
Inference by Google
136.0
From 595 benchmarks. Plenty of data behind it.
110 ±9
Coding IQ 110.0, 95% interval 102–119. 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$21.601M
49.8
Fair value (49.8). Costs per task about what its benchmark results predict. Plenty of data behind it.
38 ±12
Terse (38 ±12). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
156.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Gemini 3.1 Pro Preview
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
priority
Inference by Google
136.0
From 595 benchmarks. Plenty of data behind it.
110 ±9
Coding IQ 110.0, 95% interval 102–119. 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$21.601M
49.8
Fair value (49.8). Costs per task about what its benchmark results predict. Plenty of data behind it.
38 ±12
Terse (38 ±12). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
156.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Gemini 3.5 Flash
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGemini 3.8 FlashWe compared release dates and version names in our catalogue.
135.9
From 393 benchmarks. Plenty of data behind it.
113 ±5
Coding IQ 113.3, 95% interval 109–118. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.50cache read $0.15$9.001M
50.2
Fair value (50.2). Costs per task about what its benchmark results predict. Plenty of data behind it.
77 ±6
Chatty (77 ±6). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
155.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Gemini 3.5 Flash
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGemini 3.8 FlashWe compared release dates and version names in our catalogue.
google/gemini-3.5-flash:batch · batch
135.9
From 393 benchmarks. Plenty of data behind it.
113 ±5
Coding IQ 113.3, 95% interval 109–118. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.75cache read $0.075$4.501M
50.2
Fair value (50.2). Costs per task about what its benchmark results predict. Plenty of data behind it.
77 ±6
Chatty (77 ±6). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
155.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Gemini 3.5 Flash
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGemini 3.8 FlashWe compared release dates and version names in our catalogue.
Inference by Google
135.9
From 393 benchmarks. Plenty of data behind it.
113 ±5
Coding IQ 113.3, 95% interval 109–118. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.50cache read $0.15$9.001M
50.2
Fair value (50.2). Costs per task about what its benchmark results predict. Plenty of data behind it.
77 ±6
Chatty (77 ±6). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
155.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Gemini 3.5 Flash
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGemini 3.8 FlashWe compared release dates and version names in our catalogue.
google/gemini-3.5-flash:batch · batch+global
Inference by Google
135.9
From 393 benchmarks. Plenty of data behind it.
113 ±5
Coding IQ 113.3, 95% interval 109–118. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.75cache read $0.075$4.501M
50.2
Fair value (50.2). Costs per task about what its benchmark results predict. Plenty of data behind it.
77 ±6
Chatty (77 ±6). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
155.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Gemini 3.5 Flash
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGemini 3.8 FlashWe compared release dates and version names in our catalogue.
flex
Inference by Google
135.9
From 393 benchmarks. Plenty of data behind it.
113 ±5
Coding IQ 113.3, 95% interval 109–118. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.75cache read $0.075$4.501M
50.2
Fair value (50.2). Costs per task about what its benchmark results predict. Plenty of data behind it.
77 ±6
Chatty (77 ±6). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
155.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Gemini 3.5 Flash
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGemini 3.8 FlashWe compared release dates and version names in our catalogue.
global
Inference by Google
135.9
From 393 benchmarks. Plenty of data behind it.
113 ±5
Coding IQ 113.3, 95% interval 109–118. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.50cache read $0.15$9.001M
50.2
Fair value (50.2). Costs per task about what its benchmark results predict. Plenty of data behind it.
77 ±6
Chatty (77 ±6). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
155.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Gemini 3.5 Flash
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGemini 3.8 FlashWe compared release dates and version names in our catalogue.
global/flex
Inference by Google
135.9
From 393 benchmarks. Plenty of data behind it.
113 ±5
Coding IQ 113.3, 95% interval 109–118. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.75cache read $0.075$4.501M
50.2
Fair value (50.2). Costs per task about what its benchmark results predict. Plenty of data behind it.
77 ±6
Chatty (77 ±6). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
155.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Gemini 3.5 Flash
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGemini 3.8 FlashWe compared release dates and version names in our catalogue.
global/priority
Inference by Google
135.9
From 393 benchmarks. Plenty of data behind it.
113 ±5
Coding IQ 113.3, 95% interval 109–118. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.70cache read $0.27$16.201M
50.2
Fair value (50.2). Costs per task about what its benchmark results predict. Plenty of data behind it.
77 ±6
Chatty (77 ±6). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
155.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Gemini 3.5 Flash
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGemini 3.8 FlashWe compared release dates and version names in our catalogue.
priority
Inference by Google
135.9
From 393 benchmarks. Plenty of data behind it.
113 ±5
Coding IQ 113.3, 95% interval 109–118. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.70cache read $0.27$16.201M
50.2
Fair value (50.2). Costs per task about what its benchmark results predict. Plenty of data behind it.
77 ±6
Chatty (77 ±6). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
155.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Qwen3.8 Flash
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
135.9
From 44 benchmarks. Plenty of data behind it.
Not enough data yet$0.15cache read $0.016$0.471M
65.8
Good value (65.8). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Qwen3.8 Flash
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Inference by Alibaba Cloud
135.9
From 44 benchmarks. Plenty of data behind it.
Not enough data yet$0.15cache read $0.016$0.47cache write $0.20984K
65.8
Good value (65.8). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Qwen3.8 Flash
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
us-east-1
Inference by Alibaba Cloud
135.9
From 44 benchmarks. Plenty of data behind it.
Not enough data yet$0.15cache read $0.016$0.47984K
65.8
Good value (65.8). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
GPT-5.6 Terra
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-6.1 TerraWe compared release dates and version names in our catalogue.
135.7
From 329 benchmarks. Plenty of data behind it.
121 ±5
Coding IQ 120.9, 95% interval 116–126. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.20$12.00cache write $2.501.1M
60.4
Good value (60.4). Cheaper per task than its benchmark results predict. Plenty of data behind it.
48 ±10
Typical (48 ±10). Generates about as many tokens as models with similar coding results. Measured at max effort. A fair amount of data behind it.
160.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-5.6 Terra
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-6.1 TerraWe compared release dates and version names in our catalogue.
openai/gpt-5.6-terra:batch · batch
135.7
From 329 benchmarks. Plenty of data behind it.
121 ±5
Coding IQ 120.9, 95% interval 116–126. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.00cache read $0.10$6.001.1M
60.4
Good value (60.4). Cheaper per task than its benchmark results predict. Plenty of data behind it.
48 ±10
Typical (48 ±10). Generates about as many tokens as models with similar coding results. Measured at max effort. A fair amount of data behind it.
160.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-5.6 Terra
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-6.1 TerraWe compared release dates and version names in our catalogue.
openai/gpt-5.6-terra-pro:batch · batch+pro
135.7
From 329 benchmarks. Plenty of data behind it.
121 ±5
Coding IQ 120.9, 95% interval 116–126. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.00cache read $0.10$6.001.1M
60.4
Good value (60.4). Cheaper per task than its benchmark results predict. Plenty of data behind it.
48 ±10
Typical (48 ±10). Generates about as many tokens as models with similar coding results. Measured at max effort. A fair amount of data behind it.
160.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-5.6 Terra
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-6.1 TerraWe compared release dates and version names in our catalogue.
openai/gpt-5.6-terra-pro · pro
135.7
From 329 benchmarks. Plenty of data behind it.
121 ±5
Coding IQ 120.9, 95% interval 116–126. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.20$12.00cache write $2.501.1M
60.4
Good value (60.4). Cheaper per task than its benchmark results predict. Plenty of data behind it.
48 ±10
Typical (48 ±10). Generates about as many tokens as models with similar coding results. Measured at max effort. A fair amount of data behind it.
160.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-5.6 Terra
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-6.1 TerraWe compared release dates and version names in our catalogue.
Inference by Microsoft Azure
135.7
From 329 benchmarks. Plenty of data behind it.
121 ±5
Coding IQ 120.9, 95% interval 116–126. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.20$12.00cache write $2.50922K
60.4
Good value (60.4). Cheaper per task than its benchmark results predict. Plenty of data behind it.
48 ±10
Typical (48 ±10). Generates about as many tokens as models with similar coding results. Measured at max effort. A fair amount of data behind it.
160.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-5.6 Terra
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-6.1 TerraWe compared release dates and version names in our catalogue.
openai/gpt-5.6-terra-pro · pro
Inference by Microsoft Azure
135.7
From 329 benchmarks. Plenty of data behind it.
121 ±5
Coding IQ 120.9, 95% interval 116–126. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.20$12.00cache write $2.50922K
60.4
Good value (60.4). Cheaper per task than its benchmark results predict. Plenty of data behind it.
48 ±10
Typical (48 ±10). Generates about as many tokens as models with similar coding results. Measured at max effort. A fair amount of data behind it.
160.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-5.6 Terra
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-6.1 TerraWe compared release dates and version names in our catalogue.
Inference by OpenAI
135.7
From 329 benchmarks. Plenty of data behind it.
121 ±5
Coding IQ 120.9, 95% interval 116–126. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.20$12.00cache write $2.50922K
60.4
Good value (60.4). Cheaper per task than its benchmark results predict. Plenty of data behind it.
48 ±10
Typical (48 ±10). Generates about as many tokens as models with similar coding results. Measured at max effort. A fair amount of data behind it.
160.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-5.6 Terra
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-6.1 TerraWe compared release dates and version names in our catalogue.
openai/gpt-5.6-terra:batch · batch
Inference by OpenAI
135.7
From 329 benchmarks. Plenty of data behind it.
121 ±5
Coding IQ 120.9, 95% interval 116–126. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.00cache read $0.10$6.001.1M
60.4
Good value (60.4). Cheaper per task than its benchmark results predict. Plenty of data behind it.
48 ±10
Typical (48 ±10). Generates about as many tokens as models with similar coding results. Measured at max effort. A fair amount of data behind it.
160.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-5.6 Terra
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-6.1 TerraWe compared release dates and version names in our catalogue.
openai/gpt-5.6-terra-pro:batch · batch+pro
Inference by OpenAI
135.7
From 329 benchmarks. Plenty of data behind it.
121 ±5
Coding IQ 120.9, 95% interval 116–126. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.00cache read $0.10$6.001.1M
60.4
Good value (60.4). Cheaper per task than its benchmark results predict. Plenty of data behind it.
48 ±10
Typical (48 ±10). Generates about as many tokens as models with similar coding results. Measured at max effort. A fair amount of data behind it.
160.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-5.6 Terra
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-6.1 TerraWe compared release dates and version names in our catalogue.
fast
Inference by OpenAI
135.7
From 329 benchmarks. Plenty of data behind it.
121 ±5
Coding IQ 120.9, 95% interval 116–126. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$4.00cache read $0.40$24.00cache write $5.00922K
60.4
Good value (60.4). Cheaper per task than its benchmark results predict. Plenty of data behind it.
48 ±10
Typical (48 ±10). Generates about as many tokens as models with similar coding results. Measured at max effort. A fair amount of data behind it.
160.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-5.6 Terra
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-6.1 TerraWe compared release dates and version names in our catalogue.
openai/gpt-5.6-terra-pro · fast+pro
Inference by OpenAI
135.7
From 329 benchmarks. Plenty of data behind it.
121 ±5
Coding IQ 120.9, 95% interval 116–126. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$4.00cache read $0.40$24.00cache write $5.00922K
60.4
Good value (60.4). Cheaper per task than its benchmark results predict. Plenty of data behind it.
48 ±10
Typical (48 ±10). Generates about as many tokens as models with similar coding results. Measured at max effort. A fair amount of data behind it.
160.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-5.6 Terra
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-6.1 TerraWe compared release dates and version names in our catalogue.
flex
Inference by OpenAI
135.7
From 329 benchmarks. Plenty of data behind it.
121 ±5
Coding IQ 120.9, 95% interval 116–126. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.00cache read $0.10$6.00cache write $1.25922K
60.4
Good value (60.4). Cheaper per task than its benchmark results predict. Plenty of data behind it.
48 ±10
Typical (48 ±10). Generates about as many tokens as models with similar coding results. Measured at max effort. A fair amount of data behind it.
160.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-5.6 Terra
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-6.1 TerraWe compared release dates and version names in our catalogue.
openai/gpt-5.6-terra-pro · flex+pro
Inference by OpenAI
135.7
From 329 benchmarks. Plenty of data behind it.
121 ±5
Coding IQ 120.9, 95% interval 116–126. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.00cache read $0.10$6.00cache write $1.25922K
60.4
Good value (60.4). Cheaper per task than its benchmark results predict. Plenty of data behind it.
48 ±10
Typical (48 ±10). Generates about as many tokens as models with similar coding results. Measured at max effort. A fair amount of data behind it.
160.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-5.6 Terra
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-6.1 TerraWe compared release dates and version names in our catalogue.
openai/gpt-5.6-terra-pro · pro
Inference by OpenAI
135.7
From 329 benchmarks. Plenty of data behind it.
121 ±5
Coding IQ 120.9, 95% interval 116–126. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.20$12.00cache write $2.50922K
60.4
Good value (60.4). Cheaper per task than its benchmark results predict. Plenty of data behind it.
48 ±10
Typical (48 ±10). Generates about as many tokens as models with similar coding results. Measured at max effort. A fair amount of data behind it.
160.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-6 Luna
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
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 $0.1251.1M
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.
openai/gpt-6-luna:batch · batch
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.
$0.05cache read $0.005$0.25cache write $0.06251.1M
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.
openai/gpt-6-luna-pro:batch · batch+pro
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.
$0.05cache read $0.005$0.25cache write $0.06251.1M
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.
openai/gpt-6-luna-pro · pro
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 $0.1251.1M
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
Inference by Amazon Web Services
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.
Inference by Microsoft Azure
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.
openai/gpt-6-luna-pro · pro
Inference by Microsoft Azure
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.
Inference by OpenAI
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.
openai/gpt-6-luna:batch · batch
Inference by OpenAI
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.
$0.05cache read $0.005$0.25cache write $0.06251.1M
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.
openai/gpt-6-luna-pro:batch · batch+pro
Inference by OpenAI
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.
$0.05cache read $0.005$0.25cache write $0.06251.1M
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.
fast
Inference by OpenAI
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.
$0.20cache read $0.02$1.00cache write $0.25922K
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.
openai/gpt-6-luna-pro · fast+pro
Inference by OpenAI
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.
$0.20cache read $0.02$1.00cache write $0.25922K
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.
flex
Inference by OpenAI
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.
$0.05cache read $0.005$0.25cache write $0.0625922K
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.
openai/gpt-6-luna-pro · flex+pro
Inference by OpenAI
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.
$0.05cache read $0.005$0.25cache write $0.0625922K
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.
openai/gpt-6-luna-pro · pro
Inference by OpenAI
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
ERNIE 5.5 Flash Preview
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
baidu/ernie-5.5-flash-preview:free · free
135.2
From 14 benchmarks. A fair amount of data behind it.
Not enough data yet$0.00$0.001MNot enough data yetNot measuredNot measured
ERNIE 5.5 Flash Preview
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
baidu/ernie-5.5-flash-preview:free · free
Inference by Baidu
135.2
From 14 benchmarks. A fair amount of data behind it.
Not enough data yet$0.00$0.001MNot enough data yetNot measuredNot measured
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.
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 $0.251.1M
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.
openai/gpt-5.6-luna:batch · batch
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.
$0.10cache read $0.01$0.601.1M
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.
openai/gpt-5.6-luna-pro:batch · batch+pro
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.
$0.10cache read $0.01$0.601.1M
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.
openai/gpt-5.6-luna-pro · pro
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 $0.251.1M
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
Inference by Amazon Web Services
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.
Inference by Microsoft Azure
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.
openai/gpt-5.6-luna-pro · pro
Inference by Microsoft Azure
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.
Inference by OpenAI
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.
openai/gpt-5.6-luna:batch · batch
Inference by OpenAI
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.
$0.10cache read $0.01$0.601.1M
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.
openai/gpt-5.6-luna-pro:batch · batch+pro
Inference by OpenAI
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.
$0.10cache read $0.01$0.601.1M
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.
fast
Inference by OpenAI
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.
$0.40cache read $0.04$2.40cache write $0.50922K
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.
openai/gpt-5.6-luna-pro · fast+pro
Inference by OpenAI
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.
$0.40cache read $0.04$2.40cache write $0.50922K
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.
flex
Inference by OpenAI
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.
$0.10cache read $0.01$0.60cache write $0.125922K
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.
openai/gpt-5.6-luna-pro · flex+pro
Inference by OpenAI
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.
$0.10cache read $0.01$0.60cache write $0.125922K
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.
openai/gpt-5.6-luna-pro · pro
Inference by OpenAI
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
Ling 3.1 Flash
🇨🇳
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 versionLing 3.2 FlashWe compared the version names in our catalogue.
135.2
From 16 benchmarks. A fair amount of data behind it.
Not enough data yet$0.06cache read $0.012$0.181M
69.6
Good value (69.6). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Ling 3.1 Flash
🇨🇳
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 versionLing 3.2 FlashWe compared the version names in our catalogue.
Inference by Novita AI
135.2
From 16 benchmarks. A fair amount of data behind it.
Not enough data yet$0.06cache read $0.012$0.181M
69.6
Good value (69.6). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Qwen3.7 Max
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Newer version
Newer versionQwen4 MaxWe compared release dates and version names in our catalogue.
134.9
From 225 benchmarks. Plenty of data behind it.
112 ±5
Coding IQ 112.2, 95% interval 107–117. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.475cache read $0.295$4.425cache write $1.84381M
44.2
Poor value (44.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
55 ±9
Typical (55 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
154.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Qwen3.7 Max
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Newer version
Newer versionQwen4 MaxWe compared release dates and version names in our catalogue.
Inference by Alibaba Cloud
134.9
From 225 benchmarks. Plenty of data behind it.
112 ±5
Coding IQ 112.2, 95% interval 107–117. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.475cache read $0.295$4.425cache write $1.8438984K
44.2
Poor value (44.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
55 ±9
Typical (55 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
154.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-5.2 Pro
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-5.5 ProWe compared the version names in our catalogue.
134.7
From 42 benchmarks. Plenty of data behind it.
Not enough data yet$21.00$168.00400K
49.6
Fair value (49.6). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
157.4
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-5.2 Pro
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-5.5 ProWe compared the version names in our catalogue.
openai/gpt-5.2-pro:batch · batch
134.7
From 42 benchmarks. Plenty of data behind it.
Not enough data yet$10.50$84.00400K
49.6
Fair value (49.6). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
157.4
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-5.2 Pro
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-5.5 ProWe compared the version names in our catalogue.
Inference by OpenAI
134.7
From 42 benchmarks. Plenty of data behind it.
Not enough data yet$21.00$168.00272K
49.6
Fair value (49.6). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
157.4
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.
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.
anthropic/claude-haiku-5.5:batch · batch
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.
$0.05cache read $0.005$0.25cache write $0.06251M
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.
Inference by Amazon Web Services
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.
Inference by Anthropic
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.
anthropic/claude-haiku-5.5:batch · batch
Inference by Anthropic
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.
$0.05cache read $0.005$0.25cache write $0.06251M
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
Inference by Microsoft Azure
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.
Inference by Claude Platform On AWS
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.
global
Inference by Google
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
MiniMax M3.1 Flash
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
134.5
From 60 benchmarks. Plenty of data behind it.
119 ±9
Coding IQ 118.7, 95% interval 109–128. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15cache read $0.015$0.601M
60.2
Good value (60.2). Cheaper per task than its benchmark results predict. Plenty of data behind it.
Not measuredNot measured
MiniMax M3.1 Flash
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Inference by Digitalocean
134.5
From 60 benchmarks. Plenty of data behind it.
119 ±9
Coding IQ 118.7, 95% interval 109–128. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15cache read $0.015$0.601M
60.2
Good value (60.2). Cheaper per task than its benchmark results predict. Plenty of data behind it.
Not measuredNot measured
MiniMax M3.1 Flash
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Inference by Fireworks AI
134.5
From 60 benchmarks. Plenty of data behind it.
119 ±9
Coding IQ 118.7, 95% interval 109–128. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15cache read $0.015$0.601M
60.2
Good value (60.2). Cheaper per task than its benchmark results predict. Plenty of data behind it.
Not measuredNot measured
MiniMax M3.1 Flash
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
nvfp4
Inference by Inferact Vllm
134.5
From 60 benchmarks. Plenty of data behind it.
119 ±9
Coding IQ 118.7, 95% interval 109–128. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15cache read $0.015$0.601M
60.2
Good value (60.2). Cheaper per task than its benchmark results predict. Plenty of data behind it.
Not measuredNot measured
MiniMax M3.1 Flash
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
fp4
Inference by Inferencenet
134.5
From 60 benchmarks. Plenty of data behind it.
119 ±9
Coding IQ 118.7, 95% interval 109–128. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15cache read $0.015$0.601M
60.2
Good value (60.2). Cheaper per task than its benchmark results predict. Plenty of data behind it.
Not measuredNot measured
MiniMax M3.1 Flash
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
fp4/us · fp4
Inference by Inferencenet
134.5
From 60 benchmarks. Plenty of data behind it.
119 ±9
Coding IQ 118.7, 95% interval 109–128. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15cache read $0.015$0.601M
60.2
Good value (60.2). Cheaper per task than its benchmark results predict. Plenty of data behind it.
Not measuredNot measured
MiniMax M3.1 Flash
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
fp4
Inference by Makora
134.5
From 60 benchmarks. Plenty of data behind it.
119 ±9
Coding IQ 118.7, 95% interval 109–128. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.17cache read $0.02$0.601M
60.2
Good value (60.2). Cheaper per task than its benchmark results predict. Plenty of data behind it.
Not measuredNot measured
MiniMax M3.1 Flash
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
fp4
Inference by Modelrun
134.5
From 60 benchmarks. Plenty of data behind it.
119 ±9
Coding IQ 118.7, 95% interval 109–128. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15cache read $0.015$0.601M
60.2
Good value (60.2). Cheaper per task than its benchmark results predict. Plenty of data behind it.
Not measuredNot measured
MiniMax M3.1 Flash
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
fp4
Inference by Nebius AI Studio
134.5
From 60 benchmarks. Plenty of data behind it.
119 ±9
Coding IQ 118.7, 95% interval 109–128. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15cache read $0.015$0.601M
60.2
Good value (60.2). Cheaper per task than its benchmark results predict. Plenty of data behind it.
Not measuredNot measured
MiniMax M3.1 Flash
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
fp8
Inference by Parasail
134.5
From 60 benchmarks. Plenty of data behind it.
119 ±9
Coding IQ 118.7, 95% interval 109–128. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15cache read $0.015$0.601M
60.2
Good value (60.2). Cheaper per task than its benchmark results predict. Plenty of data behind it.
Not measuredNot measured
MiniMax M3.1 Flash
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Inference by SambaNova
134.5
From 60 benchmarks. Plenty of data behind it.
119 ±9
Coding IQ 118.7, 95% interval 109–128. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15cache read $0.015$0.601M
60.2
Good value (60.2). Cheaper per task than its benchmark results predict. Plenty of data behind it.
Not measuredNot measured
MiniMax M3.1 Flash
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
fp8
Inference by Streamlake
134.5
From 60 benchmarks. Plenty of data behind it.
119 ±9
Coding IQ 118.7, 95% interval 109–128. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.135cache read $0.0135$0.541M
60.2
Good value (60.2). Cheaper per task than its benchmark results predict. Plenty of data behind it.
Not measuredNot measured
MiniMax M3.1 Flash
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Inference by Together AI
134.5
From 60 benchmarks. Plenty of data behind it.
119 ±9
Coding IQ 118.7, 95% interval 109–128. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15cache read $0.015$0.601M
60.2
Good value (60.2). Cheaper per task than its benchmark results predict. Plenty of data behind it.
Not measuredNot measured
MiniMax M3.1 Flash
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
nvfp4
Inference by Wafer
134.5
From 60 benchmarks. Plenty of data behind it.
119 ±9
Coding IQ 118.7, 95% interval 109–128. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.135cache read $0.0135$0.541M
60.2
Good value (60.2). Cheaper per task than its benchmark results predict. Plenty of data behind it.
Not measuredNot measured
Gemini 3.6 Flash
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGemini 3.8 FlashWe compared release dates and version names in our catalogue.
134.4
From 267 benchmarks. Plenty of data behind it.
112 ±8
Coding IQ 111.8, 95% interval 103–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.75cache read $0.075$3.751M
50.6
Fair value (50.6). Costs per task about what 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. Little data behind it, so treat it as a rough estimate.
155.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Gemini 3.6 Flash
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGemini 3.8 FlashWe compared release dates and version names in our catalogue.
google/gemini-3.6-flash:batch · batch
134.4
From 267 benchmarks. Plenty of data behind it.
112 ±8
Coding IQ 111.8, 95% interval 103–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.375cache read $0.0375$1.8751M
50.6
Fair value (50.6). Costs per task about what 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. Little data behind it, so treat it as a rough estimate.
155.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Gemini 3.6 Flash
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGemini 3.8 FlashWe compared release dates and version names in our catalogue.
Inference by Google
134.4
From 267 benchmarks. Plenty of data behind it.
112 ±8
Coding IQ 111.8, 95% interval 103–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.75cache read $0.075$3.751M
50.6
Fair value (50.6). Costs per task about what 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. Little data behind it, so treat it as a rough estimate.
155.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Gemini 3.6 Flash
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGemini 3.8 FlashWe compared release dates and version names in our catalogue.
google/gemini-3.6-flash:batch · batch+global
Inference by Google
134.4
From 267 benchmarks. Plenty of data behind it.
112 ±8
Coding IQ 111.8, 95% interval 103–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.375cache read $0.0375$1.8751M
50.6
Fair value (50.6). Costs per task about what 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. Little data behind it, so treat it as a rough estimate.
155.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Gemini 3.6 Flash
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGemini 3.8 FlashWe compared release dates and version names in our catalogue.
flex
Inference by Google
134.4
From 267 benchmarks. Plenty of data behind it.
112 ±8
Coding IQ 111.8, 95% interval 103–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.375cache read $0.0375$1.8751M
50.6
Fair value (50.6). Costs per task about what 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. Little data behind it, so treat it as a rough estimate.
155.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Gemini 3.6 Flash
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGemini 3.8 FlashWe compared release dates and version names in our catalogue.
global
Inference by Google
134.4
From 267 benchmarks. Plenty of data behind it.
112 ±8
Coding IQ 111.8, 95% interval 103–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.75cache read $0.075$3.751M
50.6
Fair value (50.6). Costs per task about what 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. Little data behind it, so treat it as a rough estimate.
155.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Gemini 3.6 Flash
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGemini 3.8 FlashWe compared release dates and version names in our catalogue.
global/priority
Inference by Google
134.4
From 267 benchmarks. Plenty of data behind it.
112 ±8
Coding IQ 111.8, 95% interval 103–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.35cache read $0.135$6.751M
50.6
Fair value (50.6). Costs per task about what 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. Little data behind it, so treat it as a rough estimate.
155.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Gemini 3.6 Flash
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGemini 3.8 FlashWe compared release dates and version names in our catalogue.
priority
Inference by Google
134.4
From 267 benchmarks. Plenty of data behind it.
112 ±8
Coding IQ 111.8, 95% interval 103–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.35cache read $0.135$6.751M
50.6
Fair value (50.6). Costs per task about what 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. Little data behind it, so treat it as a rough estimate.
155.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
MiMo V2.6 Flash
🇨🇳
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.
134.3
From 154 benchmarks. Plenty of data behind it.
116 ±7
Coding IQ 115.7, 95% interval 109–123. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.14cache read $0.0028$0.281M
78.3
Good value (78.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
62 ±9
Chatty (62 ±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
MiMo V2.6 Flash
🇨🇳
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.
fp8
Inference by Cohere
134.3
From 154 benchmarks. Plenty of data behind it.
116 ±7
Coding IQ 115.7, 95% interval 109–123. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.14cache read $0.003$0.281M
78.3
Good value (78.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
62 ±9
Chatty (62 ±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
MiMo V2.6 Flash
🇨🇳
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.
fp4
Inference by Darkbloom
134.3
From 154 benchmarks. Plenty of data behind it.
116 ±7
Coding IQ 115.7, 95% interval 109–123. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.10cache read $0.0028$0.2833K
78.3
Good value (78.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
62 ±9
Chatty (62 ±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
MiMo V2.6 Flash
🇨🇳
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.
fp8
Inference by DeepInfra
134.3
From 154 benchmarks. Plenty of data behind it.
116 ±7
Coding IQ 115.7, 95% interval 109–123. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.14cache read $0.0028$0.281M
78.3
Good value (78.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
62 ±9
Chatty (62 ±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
MiMo V2.6 Flash
🇨🇳
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.
fp8
Inference by Makora
134.3
From 154 benchmarks. Plenty of data behind it.
116 ±7
Coding IQ 115.7, 95% interval 109–123. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.20cache read $0.015$0.401M
78.3
Good value (78.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
62 ±9
Chatty (62 ±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
MiMo V2.6 Flash
🇨🇳
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.
fp8
Inference by Tenstorrent
134.3
From 154 benchmarks. Plenty of data behind it.
116 ±7
Coding IQ 115.7, 95% interval 109–123. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.165cache read $0.004$0.331M
78.3
Good value (78.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
62 ±9
Chatty (62 ±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
MiMo V2.6 Flash
🇨🇳
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.
fp8
Inference by Venice
134.3
From 154 benchmarks. Plenty of data behind it.
116 ±7
Coding IQ 115.7, 95% interval 109–123. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.175cache read $0.0038$0.351M
78.3
Good value (78.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
62 ±9
Chatty (62 ±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
MiMo V2.6 Flash
🇨🇳
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.
fp8
Inference by Xiaomi
134.3
From 154 benchmarks. Plenty of data behind it.
116 ±7
Coding IQ 115.7, 95% interval 109–123. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.14cache read $0.0028$0.281M
78.3
Good value (78.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
62 ±9
Chatty (62 ±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
Fugu Ultra
🇯🇵
Maker headquartered in JP, according to the company's own website. The citation is on the model page.
134.2
From 9 benchmarks. A fair amount of data behind it.
113 ±8
Coding IQ 113.4, 95% interval 106–121. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.00cache read $0.50$30.001MNot enough data yetNot measuredNot measured
Fugu Ultra
🇯🇵
Maker headquartered in JP, according to the company's own website. The citation is on the model page.
Inference by Sakana AI
134.2
From 9 benchmarks. A fair amount of data behind it.
113 ±8
Coding IQ 113.4, 95% interval 106–121. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$5.00cache read $0.50$30.001MNot enough data yetNot measuredNot measured
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.
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.
anthropic/claude-opus-4.5:batch · batch
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.
$2.50cache read $0.25$12.50cache write $3.125200K
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.
Inference by Amazon Web Services
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.
Inference by Anthropic
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
Inference by Microsoft Azure
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.
Inference by Claude Platform On AWS
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
Inference by Google
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
GPT-5.1 Codex Max
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
134.0
From 11 benchmarks. A fair amount of data behind it.
112 ±9
Coding IQ 111.7, 95% interval 103–121. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.25cache read $0.125$10.00400K
47.0
Poor value (47.0). Costs more per task than its benchmark results predict. A fair amount 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
GPT-5.1 Codex Max
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Inference by Microsoft Azure
134.0
From 11 benchmarks. A fair amount of data behind it.
112 ±9
Coding IQ 111.7, 95% interval 103–121. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.25cache read $0.125$10.00272K
47.0
Poor value (47.0). Costs more per task than its benchmark results predict. A fair amount 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
GLM 5.2
🇨🇳
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.
133.9
From 361 benchmarks. Plenty of data behind it.
113 ±9
Coding IQ 113.3, 95% interval 105–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.62cache read $0.14$2.421M
45.9
Poor value (45.9). Costs more per task than its benchmark results predict. Plenty of data behind it.
58 ±10
Chatty (58 ±10). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
153.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.2
🇨🇳
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.
z-ai/glm-5.2:batch · batch
133.9
From 361 benchmarks. Plenty of data behind it.
113 ±9
Coding IQ 113.3, 95% interval 105–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.322cache read $0.109$0.9891M
45.9
Poor value (45.9). Costs more per task than its benchmark results predict. Plenty of data behind it.
58 ±10
Chatty (58 ±10). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
153.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.2
🇨🇳
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.
fast · fp8
Inference by Alibaba Cloud
133.9
From 361 benchmarks. Plenty of data behind it.
113 ±9
Coding IQ 113.3, 95% interval 105–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.31cache read $0.462$7.261M
45.9
Poor value (45.9). Costs more per task than its benchmark results predict. Plenty of data behind it.
58 ±10
Chatty (58 ±10). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
153.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.2
🇨🇳
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.
fp8
Inference by Alibaba Cloud
133.9
From 361 benchmarks. Plenty of data behind it.
113 ±9
Coding IQ 113.3, 95% interval 105–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.966cache read $0.1932$3.0361M
45.9
Poor value (45.9). Costs more per task than its benchmark results predict. Plenty of data behind it.
58 ±10
Chatty (58 ±10). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
153.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.2
🇨🇳
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.
fp8/us-east-1 · fp8
Inference by Alibaba Cloud
133.9
From 361 benchmarks. Plenty of data behind it.
113 ±9
Coding IQ 113.3, 95% interval 105–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.12cache read $0.224$3.521M
45.9
Poor value (45.9). Costs more per task than its benchmark results predict. Plenty of data behind it.
58 ±10
Chatty (58 ±10). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
153.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.2
🇨🇳
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.
fp8
Inference by Ambient
133.9
From 361 benchmarks. Plenty of data behind it.
113 ±9
Coding IQ 113.3, 95% interval 105–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.60cache read $0.15$2.00203K
45.9
Poor value (45.9). Costs more per task than its benchmark results predict. Plenty of data behind it.
58 ±10
Chatty (58 ±10). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
153.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.2
🇨🇳
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.
fast · fp4
Inference by Baidu
133.9
From 361 benchmarks. Plenty of data behind it.
113 ±9
Coding IQ 113.3, 95% interval 105–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.25cache read $0.56$7.881M
45.9
Poor value (45.9). Costs more per task than its benchmark results predict. Plenty of data behind it.
58 ±10
Chatty (58 ±10). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
153.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.2
🇨🇳
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.
fp8
Inference by Baidu
133.9
From 361 benchmarks. Plenty of data behind it.
113 ±9
Coding IQ 113.3, 95% interval 105–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.189cache read $0.0351$0.5941M
45.9
Poor value (45.9). Costs more per task than its benchmark results predict. Plenty of data behind it.
58 ±10
Chatty (58 ±10). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
153.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.2
🇨🇳
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.
fast · fp8
Inference by Baseten
133.9
From 361 benchmarks. Plenty of data behind it.
113 ±9
Coding IQ 113.3, 95% interval 105–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.10cache read $0.21$6.601M
45.9
Poor value (45.9). Costs more per task than its benchmark results predict. Plenty of data behind it.
58 ±10
Chatty (58 ±10). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
153.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.2
🇨🇳
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.
fp8
Inference by Baseten
133.9
From 361 benchmarks. Plenty of data behind it.
113 ±9
Coding IQ 113.3, 95% interval 105–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.40cache read $0.14$4.401M
45.9
Poor value (45.9). Costs more per task than its benchmark results predict. Plenty of data behind it.
58 ±10
Chatty (58 ±10). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
153.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.2
🇨🇳
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.
fp8/us · fp8
Inference by Baseten
133.9
From 361 benchmarks. Plenty of data behind it.
113 ±9
Coding IQ 113.3, 95% interval 105–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.40cache read $0.14$4.401M
45.9
Poor value (45.9). Costs more per task than its benchmark results predict. Plenty of data behind it.
58 ±10
Chatty (58 ±10). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
153.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.2
🇨🇳
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.
us/fast · fp8
Inference by Baseten
133.9
From 361 benchmarks. Plenty of data behind it.
113 ±9
Coding IQ 113.3, 95% interval 105–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.10cache read $0.21$6.601M
45.9
Poor value (45.9). Costs more per task than its benchmark results predict. Plenty of data behind it.
58 ±10
Chatty (58 ±10). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
153.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.2
🇨🇳
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.
fp4
Inference by Coreweave
133.9
From 361 benchmarks. Plenty of data behind it.
113 ±9
Coding IQ 113.3, 95% interval 105–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.62cache read $0.14$2.421M
45.9
Poor value (45.9). Costs more per task than its benchmark results predict. Plenty of data behind it.
58 ±10
Chatty (58 ±10). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
153.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.2
🇨🇳
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.
fp4
Inference by DeepInfra
133.9
From 361 benchmarks. Plenty of data behind it.
113 ±9
Coding IQ 113.3, 95% interval 105–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.5625cache read $0.105$1.801M
45.9
Poor value (45.9). Costs more per task than its benchmark results predict. Plenty of data behind it.
58 ±10
Chatty (58 ±10). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
153.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.2
🇨🇳
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.
fp4/flex · fp4
Inference by DeepInfra
133.9
From 361 benchmarks. Plenty of data behind it.
113 ±9
Coding IQ 113.3, 95% interval 105–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.45cache read $0.084$1.441M
45.9
Poor value (45.9). Costs more per task than its benchmark results predict. Plenty of data behind it.
58 ±10
Chatty (58 ±10). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
153.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.2
🇨🇳
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.
fp4/priority · fp4
Inference by DeepInfra
133.9
From 361 benchmarks. Plenty of data behind it.
113 ±9
Coding IQ 113.3, 95% interval 105–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.8438cache read $0.1575$2.701M
45.9
Poor value (45.9). Costs more per task than its benchmark results predict. Plenty of data behind it.
58 ±10
Chatty (58 ±10). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
153.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.2
🇨🇳
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.
Inference by Digitalocean
133.9
From 361 benchmarks. Plenty of data behind it.
113 ±9
Coding IQ 113.3, 95% interval 105–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.70cache read $0.105$2.201M
45.9
Poor value (45.9). Costs more per task than its benchmark results predict. Plenty of data behind it.
58 ±10
Chatty (58 ±10). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
153.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.2
🇨🇳
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.
Inference by Friendli AI
133.9
From 361 benchmarks. Plenty of data behind it.
113 ±9
Coding IQ 113.3, 95% interval 105–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.40cache read $0.26$4.401M
45.9
Poor value (45.9). Costs more per task than its benchmark results predict. Plenty of data behind it.
58 ±10
Chatty (58 ±10). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
153.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.2
🇨🇳
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.
eu
Inference by Mistral AI
133.9
From 361 benchmarks. Plenty of data behind it.
113 ±9
Coding IQ 113.3, 95% interval 105–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.54cache read $0.154$4.841M
45.9
Poor value (45.9). Costs more per task than its benchmark results predict. Plenty of data behind it.
58 ±10
Chatty (58 ±10). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
153.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.2
🇨🇳
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.
zdr
Inference by Mistral AI
133.9
From 361 benchmarks. Plenty of data behind it.
113 ±9
Coding IQ 113.3, 95% interval 105–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.40cache read $0.14$4.401M
45.9
Poor value (45.9). Costs more per task than its benchmark results predict. Plenty of data behind it.
58 ±10
Chatty (58 ±10). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
153.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.2
🇨🇳
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.
z-ai/glm-5.2:batch · batch+fp8 · fp8
Inference by Morph
133.9
From 361 benchmarks. Plenty of data behind it.
113 ±9
Coding IQ 113.3, 95% interval 105–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.322cache read $0.109$0.9891M
45.9
Poor value (45.9). Costs more per task than its benchmark results predict. Plenty of data behind it.
58 ±10
Chatty (58 ±10). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
153.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.2
🇨🇳
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.
fp8
Inference by Morph
133.9
From 361 benchmarks. Plenty of data behind it.
113 ±9
Coding IQ 113.3, 95% interval 105–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.643cache read $0.217$1.9781M
45.9
Poor value (45.9). Costs more per task than its benchmark results predict. Plenty of data behind it.
58 ±10
Chatty (58 ±10). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
153.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.2
🇨🇳
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.
fp4
Inference by Nebius AI Studio
133.9
From 361 benchmarks. Plenty of data behind it.
113 ±9
Coding IQ 113.3, 95% interval 105–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.40cache read $0.14$4.401M
45.9
Poor value (45.9). Costs more per task than its benchmark results predict. Plenty of data behind it.
58 ±10
Chatty (58 ±10). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
153.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.2
🇨🇳
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.
fp8
Inference by Novita AI
133.9
From 361 benchmarks. Plenty of data behind it.
113 ±9
Coding IQ 113.3, 95% interval 105–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.77cache read $0.143$2.421M
45.9
Poor value (45.9). Costs more per task than its benchmark results predict. Plenty of data behind it.
58 ±10
Chatty (58 ±10). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
153.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.2
🇨🇳
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.
fp4
Inference by Parasail
133.9
From 361 benchmarks. Plenty of data behind it.
113 ±9
Coding IQ 113.3, 95% interval 105–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.40cache read $0.26$4.40262K
45.9
Poor value (45.9). Costs more per task than its benchmark results predict. Plenty of data behind it.
58 ±10
Chatty (58 ±10). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
153.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.2
🇨🇳
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.
fp4
Inference by Relace
133.9
From 361 benchmarks. Plenty of data behind it.
113 ±9
Coding IQ 113.3, 95% interval 105–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.31cache read $0.075$2.401M
45.9
Poor value (45.9). Costs more per task than its benchmark results predict. Plenty of data behind it.
58 ±10
Chatty (58 ±10). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
153.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.2
🇨🇳
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.
fp8
Inference by SiliconFlow
133.9
From 361 benchmarks. Plenty of data behind it.
113 ±9
Coding IQ 113.3, 95% interval 105–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.651cache read $0.13$2.0461M
45.9
Poor value (45.9). Costs more per task than its benchmark results predict. Plenty of data behind it.
58 ±10
Chatty (58 ±10). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
153.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.2
🇨🇳
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.
fp8
Inference by Streamlake
133.9
From 361 benchmarks. Plenty of data behind it.
113 ±9
Coding IQ 113.3, 95% interval 105–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.28cache read $0.052$0.881M
45.9
Poor value (45.9). Costs more per task than its benchmark results predict. Plenty of data behind it.
58 ±10
Chatty (58 ±10). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
153.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.2
🇨🇳
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.
Inference by Together AI
133.9
From 361 benchmarks. Plenty of data behind it.
113 ±9
Coding IQ 113.3, 95% interval 105–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.40cache read $0.26$4.401M
45.9
Poor value (45.9). Costs more per task than its benchmark results predict. Plenty of data behind it.
58 ±10
Chatty (58 ±10). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
153.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.2
🇨🇳
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.
fp8
Inference by Venice
133.9
From 361 benchmarks. Plenty of data behind it.
113 ±9
Coding IQ 113.3, 95% interval 105–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.40cache read $0.26$4.401M
45.9
Poor value (45.9). Costs more per task than its benchmark results predict. Plenty of data behind it.
58 ±10
Chatty (58 ±10). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
153.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.2
🇨🇳
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.
fp4
Inference by Wafer
133.9
From 361 benchmarks. Plenty of data behind it.
113 ±9
Coding IQ 113.3, 95% interval 105–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.19cache read $0.18$8.001M
45.9
Poor value (45.9). Costs more per task than its benchmark results predict. Plenty of data behind it.
58 ±10
Chatty (58 ±10). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
153.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.2
🇨🇳
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.
us · fp4
Inference by Wafer
133.9
From 361 benchmarks. Plenty of data behind it.
113 ±9
Coding IQ 113.3, 95% interval 105–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.007cache read $0.006$6.801M
45.9
Poor value (45.9). Costs more per task than its benchmark results predict. Plenty of data behind it.
58 ±10
Chatty (58 ±10). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
153.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.2
🇨🇳
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.
fp8
Inference by Z.ai
133.9
From 361 benchmarks. Plenty of data behind it.
113 ±9
Coding IQ 113.3, 95% interval 105–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.40cache read $0.26$4.401M
45.9
Poor value (45.9). Costs more per task than its benchmark results predict. Plenty of data behind it.
58 ±10
Chatty (58 ±10). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
153.1
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.
$3.00cache 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.
anthropic/claude-sonnet-4.6:batch · batch
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.
$1.50cache read $0.15$7.50cache write $1.8751M
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
Inference by Amazon Web Services
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.
Inference by Anthropic
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
Inference by Microsoft Azure
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.
Inference by Claude Platform On AWS
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
Inference by Google
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
GLM 5.3 Flash
🇨🇳
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.
133.6
From 266 benchmarks. Plenty of data behind it.
113 ±8
Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.0399cache read $0.03$0.07841M
65.3
Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
68 ±11
Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
153.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3 Flash
🇨🇳
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.
z-ai/glm-5.3-flash:batch · batch
133.6
From 266 benchmarks. Plenty of data behind it.
113 ±8
Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.023cache read $0.009$0.0681M
65.3
Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
68 ±11
Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
153.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3 Flash
🇨🇳
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.
fp8
Inference by Baidu
133.6
From 266 benchmarks. Plenty of data behind it.
113 ±8
Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15cache read $0.03$0.501M
65.3
Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
68 ±11
Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
153.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3 Flash
🇨🇳
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.
fp8
Inference by Baseten
133.6
From 266 benchmarks. Plenty of data behind it.
113 ±8
Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15cache read $0.03$0.501M
65.3
Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
68 ±11
Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
153.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3 Flash
🇨🇳
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.
nvfp4
Inference by Cohere
133.6
From 266 benchmarks. Plenty of data behind it.
113 ±8
Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.105cache read $0.02$0.341M
65.3
Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
68 ±11
Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
153.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3 Flash
🇨🇳
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.
nvfp4
Inference by Coreweave
133.6
From 266 benchmarks. Plenty of data behind it.
113 ±8
Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.12cache read $0.02$0.381M
65.3
Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
68 ±11
Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
153.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3 Flash
🇨🇳
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.
fp4
Inference by Crusoe
133.6
From 266 benchmarks. Plenty of data behind it.
113 ±8
Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15cache read $0.03$0.501M
65.3
Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
68 ±11
Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
153.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3 Flash
🇨🇳
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.
fp4
Inference by Darkbloom
133.6
From 266 benchmarks. Plenty of data behind it.
113 ±8
Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.13cache read $0.024$0.3633K
65.3
Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
68 ±11
Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
153.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3 Flash
🇨🇳
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.
z-ai/glm-5.3-flash:batch · batch+fp4 · fp4
Inference by DeepInfra
133.6
From 266 benchmarks. Plenty of data behind it.
113 ±8
Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.12cache read $0.024$0.401M
65.3
Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
68 ±11
Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
153.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3 Flash
🇨🇳
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.
fp4
Inference by DeepInfra
133.6
From 266 benchmarks. Plenty of data behind it.
113 ±8
Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.1005cache read $0.0201$0.3351M
65.3
Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
68 ±11
Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
153.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3 Flash
🇨🇳
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.
Inference by Dekallm
133.6
From 266 benchmarks. Plenty of data behind it.
113 ±8
Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.10cache read $0.03$0.501M
65.3
Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
68 ±11
Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
153.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3 Flash
🇨🇳
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.
Inference by Digitalocean
133.6
From 266 benchmarks. Plenty of data behind it.
113 ±8
Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.0975cache read $0.0195$0.3251M
65.3
Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
68 ±11
Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
153.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3 Flash
🇨🇳
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.
Inference by Fireworks AI
133.6
From 266 benchmarks. Plenty of data behind it.
113 ±8
Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15cache read $0.03$0.501M
65.3
Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
68 ±11
Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
153.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3 Flash
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
us
Inference by Fireworks AI
133.6
From 266 benchmarks. Plenty of data behind it.
113 ±8
Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.225cache read $0.045$0.751M
65.3
Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
68 ±11
Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
153.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3 Flash
🇨🇳
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.
Inference by Friendli AI
133.6
From 266 benchmarks. Plenty of data behind it.
113 ±8
Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15cache read $0.03$0.501M
65.3
Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
68 ±11
Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
153.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3 Flash
🇨🇳
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.
fp8
Inference by Inceptron
133.6
From 266 benchmarks. Plenty of data behind it.
113 ±8
Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.16cache read $0.04$0.501M
65.3
Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
68 ±11
Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
153.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3 Flash
🇨🇳
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.
fp4
Inference by Inferencenet
133.6
From 266 benchmarks. Plenty of data behind it.
113 ±8
Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.108cache read $0.035$0.351M
65.3
Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
68 ±11
Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
153.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3 Flash
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
us · fp4
Inference by Inferencenet
133.6
From 266 benchmarks. Plenty of data behind it.
113 ±8
Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.108cache read $0.035$0.351M
65.3
Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
68 ±11
Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
153.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3 Flash
🇨🇳
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.
Inference by Kt
133.6
From 266 benchmarks. Plenty of data behind it.
113 ±8
Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15cache read $0.03$0.501M
65.3
Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
68 ±11
Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
153.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3 Flash
🇨🇳
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.
fp4
Inference by Makora
133.6
From 266 benchmarks. Plenty of data behind it.
113 ±8
Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.14cache read $0.03$0.241M
65.3
Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
68 ±11
Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
153.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3 Flash
🇨🇳
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.
Inference by Mistral AI
133.6
From 266 benchmarks. Plenty of data behind it.
113 ±8
Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15cache read $0.03$0.501M
65.3
Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
68 ±11
Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
153.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3 Flash
🇨🇳
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.
fp4
Inference by Modal
133.6
From 266 benchmarks. Plenty of data behind it.
113 ±8
Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15cache read $0.03$0.501M
65.3
Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
68 ±11
Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
153.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3 Flash
🇨🇳
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.
z-ai/glm-5.3-flash:batch · batch+fp8 · fp8
Inference by Morph
133.6
From 266 benchmarks. Plenty of data behind it.
113 ±8
Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.024cache read $0.01$0.0691M
65.3
Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
68 ±11
Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
153.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3 Flash
🇨🇳
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.
fp8
Inference by Morph
133.6
From 266 benchmarks. Plenty of data behind it.
113 ±8
Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.101cache read $0.05$0.291M
65.3
Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
68 ±11
Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
153.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3 Flash
🇨🇳
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.
fp8
Inference by Near AI
133.6
From 266 benchmarks. Plenty of data behind it.
113 ±8
Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.08cache read $0.012$0.501M
65.3
Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
68 ±11
Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
153.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3 Flash
🇨🇳
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.
fp4
Inference by Nebius AI Studio
133.6
From 266 benchmarks. Plenty of data behind it.
113 ±8
Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15cache read $0.03$0.501M
65.3
Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
68 ±11
Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
153.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3 Flash
🇨🇳
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.
fp8
Inference by Novita AI
133.6
From 266 benchmarks. Plenty of data behind it.
113 ±8
Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.084cache read $0.0168$0.281M
65.3
Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
68 ±11
Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
153.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3 Flash
🇨🇳
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.
fp4
Inference by Openinference
133.6
From 266 benchmarks. Plenty of data behind it.
113 ±8
Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.05cache read $0.025$0.451M
65.3
Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
68 ±11
Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
153.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3 Flash
🇨🇳
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.
fast · fp4
Inference by Parasail
133.6
From 266 benchmarks. Plenty of data behind it.
113 ±8
Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.1875cache read $0.0375$0.6251M
65.3
Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
68 ±11
Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
153.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3 Flash
🇨🇳
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.
fp8
Inference by Parasail
133.6
From 266 benchmarks. Plenty of data behind it.
113 ±8
Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15cache read $0.03$0.501M
65.3
Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
68 ±11
Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
153.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3 Flash
🇨🇳
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.
nvfp4
Inference by Particle AI
133.6
From 266 benchmarks. Plenty of data behind it.
113 ±8
Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.13cache read $0.04$0.651M
65.3
Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
68 ±11
Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
153.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3 Flash
🇨🇳
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.
nvfp4/flex · nvfp4
Inference by Particle AI
133.6
From 266 benchmarks. Plenty of data behind it.
113 ±8
Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.065cache read $0.02$0.3251M
65.3
Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
68 ±11
Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
153.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3 Flash
🇨🇳
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.
Inference by Reka AI
133.6
From 266 benchmarks. Plenty of data behind it.
113 ±8
Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.12cache read $0.03$0.301M
65.3
Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
68 ±11
Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
153.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3 Flash
🇨🇳
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.
fp4
Inference by Relace
133.6
From 266 benchmarks. Plenty of data behind it.
113 ±8
Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.0399cache read $0.03$0.07841M
65.3
Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
68 ±11
Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
153.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3 Flash
🇨🇳
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.
z-ai/glm-5.3-flash:batch · batch+fp4 · fp4
Inference by Sail Research
133.6
From 266 benchmarks. Plenty of data behind it.
113 ±8
Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.05cache read $0.01$0.181M
65.3
Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
68 ±11
Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
153.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3 Flash
🇨🇳
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.
fp4
Inference by Sail Research
133.6
From 266 benchmarks. Plenty of data behind it.
113 ±8
Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.175cache read $0.0225$0.6251M
65.3
Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
68 ±11
Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
153.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3 Flash
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
us · fp4
Inference by Sail Research
133.6
From 266 benchmarks. Plenty of data behind it.
113 ±8
Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.175cache read $0.0225$0.6251M
65.3
Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
68 ±11
Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
153.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3 Flash
🇨🇳
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.
fp8
Inference by SiliconFlow
133.6
From 266 benchmarks. Plenty of data behind it.
113 ±8
Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.10cache read $0.03$0.401M
65.3
Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
68 ±11
Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
153.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3 Flash
🇨🇳
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.
fp8
Inference by Streamlake
133.6
From 266 benchmarks. Plenty of data behind it.
113 ±8
Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.0885cache read $0.0177$0.2951M
65.3
Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
68 ±11
Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
153.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3 Flash
🇨🇳
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.
fp8
Inference by Tenstorrent
133.6
From 266 benchmarks. Plenty of data behind it.
113 ±8
Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.075cache read $0.015$0.25262K
65.3
Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
68 ±11
Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
153.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3 Flash
🇨🇳
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.
Inference by Together AI
133.6
From 266 benchmarks. Plenty of data behind it.
113 ±8
Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15cache read $0.03$0.501M
65.3
Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
68 ±11
Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
153.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3 Flash
🇨🇳
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.
z-ai/glm-5.3-flash:batch · batch
Inference by Together AI
133.6
From 266 benchmarks. Plenty of data behind it.
113 ±8
Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.023cache read $0.009$0.0681M
65.3
Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
68 ±11
Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
153.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3 Flash
🇨🇳
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.
Inference by Venice
133.6
From 266 benchmarks. Plenty of data behind it.
113 ±8
Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15cache read $0.03$0.501M
65.3
Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
68 ±11
Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
153.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3 Flash
🇨🇳
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.
nvfp4
Inference by Wafer
133.6
From 266 benchmarks. Plenty of data behind it.
113 ±8
Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.065cache read $0.064$0.241M
65.3
Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
68 ±11
Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
153.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3 Flash
🇨🇳
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
us · nvfp4
Inference by Wafer
133.6
From 266 benchmarks. Plenty of data behind it.
113 ±8
Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.042cache read $0.041$0.1841M
65.3
Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
68 ±11
Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
153.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.3 Flash
🇨🇳
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.
fp8
Inference by Z.ai
133.6
From 266 benchmarks. Plenty of data behind it.
113 ±8
Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.15cache read $0.03$0.501M
65.3
Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it.
68 ±11
Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it.
153.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-5.3 Codex
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
133.6
From 51 benchmarks. Plenty of data behind it.
114 ±8
Coding IQ 113.7, 95% interval 106–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.75cache read $0.175$14.00400K
59.7
Good value (59.7). Cheaper per task than its benchmark results predict. Plenty of data behind it.
46 ±9
Typical (46 ±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
GPT-5.3 Codex
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Inference by Microsoft Azure
133.6
From 51 benchmarks. Plenty of data behind it.
114 ±8
Coding IQ 113.7, 95% interval 106–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.75cache read $0.175$14.00272K
59.7
Good value (59.7). Cheaper per task than its benchmark results predict. Plenty of data behind it.
46 ±9
Typical (46 ±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
GPT-5.3 Codex
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Inference by OpenAI
133.6
From 51 benchmarks. Plenty of data behind it.
114 ±8
Coding IQ 113.7, 95% interval 106–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.75cache read $0.175$14.00272K
59.7
Good value (59.7). Cheaper per task than its benchmark results predict. Plenty of data behind it.
46 ±9
Typical (46 ±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
GPT-5.3 Codex
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
fast
Inference by OpenAI
133.6
From 51 benchmarks. Plenty of data behind it.
114 ±8
Coding IQ 113.7, 95% interval 106–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.50cache read $0.35$28.00272K
59.7
Good value (59.7). Cheaper per task than its benchmark results predict. Plenty of data behind it.
46 ±9
Typical (46 ±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
GPT 5.2
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT 6We compared the version names in our catalogue.
133.4
From 440 benchmarks. Plenty of data behind it.
112 ±7
Coding IQ 111.5, 95% interval 105–118. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.75cache read $0.175$14.00400K
56.6
Good value (56.6). Cheaper per task than its benchmark results predict. Plenty of data behind it.
49 ±14
Typical (49 ±14). 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.
154.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 5.2
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT 6We compared the version names in our catalogue.
openai/gpt-5.2:batch · batch
133.4
From 440 benchmarks. Plenty of data behind it.
112 ±7
Coding IQ 111.5, 95% interval 105–118. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.875cache read $0.0875$7.00400K
56.6
Good value (56.6). Cheaper per task than its benchmark results predict. Plenty of data behind it.
49 ±14
Typical (49 ±14). 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.
154.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 5.2
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT 6We compared the version names in our catalogue.
Inference by Microsoft Azure
133.4
From 440 benchmarks. Plenty of data behind it.
112 ±7
Coding IQ 111.5, 95% interval 105–118. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.75cache read $0.175$14.00272K
56.6
Good value (56.6). Cheaper per task than its benchmark results predict. Plenty of data behind it.
49 ±14
Typical (49 ±14). 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.
154.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 5.2
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT 6We compared the version names in our catalogue.
Inference by OpenAI
133.4
From 440 benchmarks. Plenty of data behind it.
112 ±7
Coding IQ 111.5, 95% interval 105–118. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.75cache read $0.175$14.00272K
56.6
Good value (56.6). Cheaper per task than its benchmark results predict. Plenty of data behind it.
49 ±14
Typical (49 ±14). 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.
154.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 5.2
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT 6We compared the version names in our catalogue.
fast
Inference by OpenAI
133.4
From 440 benchmarks. Plenty of data behind it.
112 ±7
Coding IQ 111.5, 95% interval 105–118. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.50cache read $0.35$28.00272K
56.6
Good value (56.6). Cheaper per task than its benchmark results predict. Plenty of data behind it.
49 ±14
Typical (49 ±14). 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.
154.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 5.2
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT 6We compared the version names in our catalogue.
flex
Inference by OpenAI
133.4
From 440 benchmarks. Plenty of data behind it.
112 ±7
Coding IQ 111.5, 95% interval 105–118. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.875cache read $0.0875$7.00272K
56.6
Good value (56.6). Cheaper per task than its benchmark results predict. Plenty of data behind it.
49 ±14
Typical (49 ±14). 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.
154.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
≈ 133
From 3 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$3.00cache read $0.75$6.00262KNot enough data yetNot measuredNot measured
Inference by Aionlabs
≈ 133
From 3 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yet$3.00cache read $0.75$6.00262KNot enough data yetNot measuredNot measured
GPT-5 Pro
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-5.5 ProWe compared release dates and version names in our catalogue.
132.8
From 14 benchmarks. Plenty of data behind it.
Not enough data yet$15.00$120.00400K
29.6
Poor value (29.6). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measured
151.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-5 Pro
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-5.5 ProWe compared release dates and version names in our catalogue.
openai/gpt-5-pro:batch · batch
132.8
From 14 benchmarks. Plenty of data behind it.
Not enough data yet$7.50$60.00400K
29.6
Poor value (29.6). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measured
151.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-5 Pro
🇺🇸
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-5.5 ProWe compared release dates and version names in our catalogue.
Inference by OpenAI
132.8
From 14 benchmarks. Plenty of data behind it.
Not enough data yet$15.00$120.00272K
29.6
Poor value (29.6). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measured
151.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API

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

How this data works