Skip to content

Listings

All listings: Llmgateway

Every listing for the models on page 4 of 13 of Llmgateway, including each model's other versions and routes. Back to Llmgateway

Sold by Llmgateway

91 listings on this page sold by Llmgateway.

Select a score for details.

About these columns
llminfo IQ
llminfo IQ (capability index). How llminfo IQ is computed
Coding IQ
llminfo Coding IQ (coding capability, its own scale). How Coding IQ is computed
Value
Value for money. 50 means as expected for its results. Above 50, cheaper per task. How Value for money works
Yap
Tokens used per coding task vs. models with the same results. Includes agents that write code. Chattiness on maths doesn't predict it. How the Yap score works
Modelllminfo IQCoding IQInput $/1MOutput $/1MMax Input TokensValueYapEpoch Capabilities Index
GPT 5
πŸ‡ΊπŸ‡Έ
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
131.7
From 584 benchmarks. Plenty of data behind it.
111Β Β±5
Coding IQ 110.8, 95% interval 106–116. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.25cache read $0.125$10.00Not published by the provider
52.5
Fair value (52.5). Costs per task about what its benchmark results predict. Plenty of data behind it.
65 Β±8
Chatty (65 Β±8). Generates more tokens than models with similar coding results. Measured at medium effort. A fair amount of data behind it.
150
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 5
πŸ‡ΊπŸ‡Έ
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
131.7
From 584 benchmarks. Plenty of data behind it.
111Β Β±5
Coding IQ 110.8, 95% interval 106–116. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.25cache read $0.125$10.00Not published by the provider
52.5
Fair value (52.5). Costs per task about what its benchmark results predict. Plenty of data behind it.
65 Β±8
Chatty (65 Β±8). Generates more tokens than models with similar coding results. Measured at medium effort. A fair amount of data behind it.
150
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Hy4 Flash
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
New
Released 16 Nov 2026
131.7
From 26 benchmarks. Plenty of data behind it.
β‰ˆ 115Β Β±24
Coding IQ 115.3, 95% interval 91–140. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.07cache read $0.003$0.2811M
65.5
Good value (65.5). Cheaper per task than its benchmark results predict. Plenty of data behind it.
40 Β±9
Terse (40 Β±9). Generates fewer tokens than models with similar coding results. Measured with reasoning off. Little data behind it, so treat it as a rough estimate.
Not measured
Qwen3 Embedding 8B
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
131.7
From 196 benchmarks. Plenty of data behind it.
Not enough data yet$0.01β€”41KNot enough data yetNot measuredNot measured
Qwen3 Embedding 8B
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Inference by DeepInfra
131.7
From 196 benchmarks. Plenty of data behind it.
Not enough data yet$0.01β€”Not published by the providerNot enough data yetNot measuredNot measured
Qwen3 Embedding 8B
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Inference by Nebius AI Studio
131.7
From 196 benchmarks. Plenty of data behind it.
Not enough data yet$0.01β€”Not published by the providerNot enough data yetNot measuredNot measured
GPT 5.1
πŸ‡ΊπŸ‡Έ
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
131.0
From 352 benchmarks. Plenty of data behind it.
107Β Β±8
Coding IQ 106.6, 95% interval 99–114. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.25cache read $0.125$10.00Not published by the provider
49.7
Fair value (49.7). Costs per task about what its benchmark results predict. Plenty of data behind it.
50 Β±9
Typical (50 Β±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.
150.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT 5.1
πŸ‡ΊπŸ‡Έ
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
131.0
From 352 benchmarks. Plenty of data behind it.
107Β Β±8
Coding IQ 106.6, 95% interval 99–114. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.25cache read $0.125$10.00Not published by the provider
49.7
Fair value (49.7). Costs per task about what its benchmark results predict. Plenty of data behind it.
50 Β±9
Typical (50 Β±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.
150.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.1
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Newer version
Newer versionGLM 5.3We compared release dates and version names in our catalogue.
130.8
From 224 benchmarks. Plenty of data behind it.
110Β Β±6
Coding IQ 110.0, 95% interval 104–116. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.38cache read $0.26$4.40205K
43.2
Poor value (43.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
51 Β±8
Typical (51 Β±8). Generates about as many tokens as models with similar coding results. Measured at default effort. A fair amount of data behind it.
150.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.1
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Newer version
Newer versionGLM 5.3We compared release dates and version names in our catalogue.
Inference by Alibaba Cloud
130.8
From 224 benchmarks. Plenty of data behind it.
110Β Β±6
Coding IQ 110.0, 95% interval 104–116. 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$4.40Not published by the provider
43.2
Poor value (43.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
51 Β±8
Typical (51 Β±8). Generates about as many tokens as models with similar coding results. Measured at default effort. A fair amount of data behind it.
150.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.1
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Newer version
Newer versionGLM 5.3We compared release dates and version names in our catalogue.
Inference by DeepInfra
130.8
From 224 benchmarks. Plenty of data behind it.
110Β Β±6
Coding IQ 110.0, 95% interval 104–116. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.05cache read $0.205$3.50Not published by the provider
43.2
Poor value (43.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
51 Β±8
Typical (51 Β±8). Generates about as many tokens as models with similar coding results. Measured at default effort. A fair amount of data behind it.
150.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.1
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Newer version
Newer versionGLM 5.3We compared release dates and version names in our catalogue.
Inference by Nebius AI Studio
130.8
From 224 benchmarks. Plenty of data behind it.
110Β Β±6
Coding IQ 110.0, 95% interval 104–116. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.40$4.40Not published by the provider
43.2
Poor value (43.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
51 Β±8
Typical (51 Β±8). Generates about as many tokens as models with similar coding results. Measured at default effort. A fair amount of data behind it.
150.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.1
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Newer version
Newer versionGLM 5.3We compared release dates and version names in our catalogue.
Inference by Novita AI
130.8
From 224 benchmarks. Plenty of data behind it.
110Β Β±6
Coding IQ 110.0, 95% interval 104–116. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.38cache read $0.26$4.40Not published by the provider
43.2
Poor value (43.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
51 Β±8
Typical (51 Β±8). Generates about as many tokens as models with similar coding results. Measured at default effort. A fair amount of data behind it.
150.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.1
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Newer version
Newer versionGLM 5.3We compared release dates and version names in our catalogue.
Inference by Together AI
130.8
From 224 benchmarks. Plenty of data behind it.
110Β Β±6
Coding IQ 110.0, 95% interval 104–116. 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$4.40Not published by the provider
43.2
Poor value (43.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
51 Β±8
Typical (51 Β±8). Generates about as many tokens as models with similar coding results. Measured at default effort. A fair amount of data behind it.
150.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5.1
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Newer version
Newer versionGLM 5.3We compared release dates and version names in our catalogue.
Inference by Z.ai
130.8
From 224 benchmarks. Plenty of data behind it.
110Β Β±6
Coding IQ 110.0, 95% interval 104–116. 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$4.40Not published by the provider
43.2
Poor value (43.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
51 Β±8
Typical (51 Β±8). Generates about as many tokens as models with similar coding results. Measured at default effort. A fair amount of data behind it.
150.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
DeepSeek V4 Pro
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
130.7
From 303 benchmarks. Plenty of data behind it.
105Β Β±7
Coding IQ 104.6, 95% interval 98–111. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.66cache read $0.022$1.981.1M
46.9
Poor value (46.9). Costs more per task than its benchmark results predict. Plenty of data behind it.
43 Β±10
Terse (43 Β±10). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
150.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
DeepSeek V4 Pro
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
deepseek-v4-pro-0813
Inference by Alibaba Cloud
130.7
From 303 benchmarks. Plenty of data behind it.
105Β Β±7
Coding IQ 104.6, 95% interval 98–111. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.32cache read $0.132$3.96Not published by the provider
46.9
Poor value (46.9). Costs more per task than its benchmark results predict. Plenty of data behind it.
43 Β±10
Terse (43 Β±10). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
150.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
DeepSeek V4 Pro
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
@cf/deepseek-ai/deepseek-v4-pro-0813
Inference by Cloudflare Workers AI
130.7
From 303 benchmarks. Plenty of data behind it.
105Β Β±7
Coding IQ 104.6, 95% interval 98–111. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.32cache read $0.044$3.96Not published by the provider
46.9
Poor value (46.9). Costs more per task than its benchmark results predict. Plenty of data behind it.
43 Β±10
Terse (43 Β±10). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
150.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
DeepSeek V4 Pro
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Inference by DeepInfra
130.7
From 303 benchmarks. Plenty of data behind it.
105Β Β±7
Coding IQ 104.6, 95% interval 98–111. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.30cache read $0.10$2.60Not published by the provider
46.9
Poor value (46.9). Costs more per task than its benchmark results predict. Plenty of data behind it.
43 Β±10
Terse (43 Β±10). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
150.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
DeepSeek V4 Pro
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Inference by DeepSeek
130.7
From 303 benchmarks. Plenty of data behind it.
105Β Β±7
Coding IQ 104.6, 95% interval 98–111. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.66cache read $0.022$1.98Not published by the provider
46.9
Poor value (46.9). Costs more per task than its benchmark results predict. Plenty of data behind it.
43 Β±10
Terse (43 Β±10). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
150.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
DeepSeek V4 Pro
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
accounts/fireworks/models/deepseek-v4-pro-0813
Inference by Fireworks AI
130.7
From 303 benchmarks. Plenty of data behind it.
105Β Β±7
Coding IQ 104.6, 95% interval 98–111. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.32cache read $0.044$3.96Not published by the provider
46.9
Poor value (46.9). Costs more per task than its benchmark results predict. Plenty of data behind it.
43 Β±10
Terse (43 Β±10). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
150.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
DeepSeek V4 Pro
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Inference by Nebius AI Studio
130.7
From 303 benchmarks. Plenty of data behind it.
105Β Β±7
Coding IQ 104.6, 95% interval 98–111. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.75$3.50Not published by the provider
46.9
Poor value (46.9). Costs more per task than its benchmark results predict. Plenty of data behind it.
43 Β±10
Terse (43 Β±10). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
150.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
DeepSeek V4 Pro
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
deepseek-ai/DeepSeek-V4-Pro-0813
Inference by Together AI
130.7
From 303 benchmarks. Plenty of data behind it.
105Β Β±7
Coding IQ 104.6, 95% interval 98–111. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.32cache read $0.13$3.96Not published by the provider
46.9
Poor value (46.9). Costs more per task than its benchmark results predict. Plenty of data behind it.
43 Β±10
Terse (43 Β±10). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
150.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Qwen3.5 397B A17B
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
130.6
From 367 benchmarks. Plenty of data behind it.
105Β Β±7
Coding IQ 104.8, 95% interval 98–112. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.60$3.60262K
48.4
Fair value (48.4). Costs per task about what its benchmark results predict. Plenty of data behind it.
46 Β±9
Typical (46 Β±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.
148
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Qwen3.5 397B A17B
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Inference by Alibaba Cloud
130.6
From 367 benchmarks. Plenty of data behind it.
105Β Β±7
Coding IQ 104.8, 95% interval 98–112. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.60$3.60Not published by the provider
48.4
Fair value (48.4). Costs per task about what its benchmark results predict. Plenty of data behind it.
46 Β±9
Typical (46 Β±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.
148
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Qwen3.5 397B A17B
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Inference by Nebius AI Studio
130.6
From 367 benchmarks. Plenty of data behind it.
105Β Β±7
Coding IQ 104.8, 95% interval 98–112. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.60$3.60Not published by the provider
48.4
Fair value (48.4). Costs per task about what its benchmark results predict. Plenty of data behind it.
46 Β±9
Typical (46 Β±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.
148
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Qwen3.5 397B A17B
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Inference by Novita AI
130.6
From 367 benchmarks. Plenty of data behind it.
105Β Β±7
Coding IQ 104.8, 95% interval 98–112. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.60$3.60Not published by the provider
48.4
Fair value (48.4). Costs per task about what its benchmark results predict. Plenty of data behind it.
46 Β±9
Typical (46 Β±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.
148
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Beam 1.0 501B A23B
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
130.0
From 84 benchmarks. Plenty of data behind it.
109Β Β±6
Coding IQ 109.0, 95% interval 103–115. 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$1.201MNot enough data yetNot measuredNot measured
Beam 1.0 501B A23B
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Inference by Together AI
130.0
From 84 benchmarks. Plenty of data behind it.
109Β Β±6
Coding IQ 109.0, 95% interval 103–115. 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$1.20Not published by the providerNot enough data yetNot measuredNot measured
Claude Sonnet 4.5
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Sonnet 5.5We compared release dates and version names in our catalogue.
anthropic.claude-sonnet-4-5-20250929-v1:0
Inference by Amazon Web Services
129.7
From 442 benchmarks. Plenty of data behind it.
107Β Β±7
Coding IQ 107.2, 95% interval 101–114. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.00cache read $0.30$15.00cache write $3.75Not published by the provider
40.2
Poor value (40.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
41 Β±8
Terse (41 Β±8). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
147.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.5
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Sonnet 5.5We compared release dates and version names in our catalogue.
anthropic.claude-sonnet-4-5-20250929-v1:0 Β· 20250929
Inference by Amazon Web Services
129.7
From 442 benchmarks. Plenty of data behind it.
107Β Β±7
Coding IQ 107.2, 95% interval 101–114. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.00cache read $0.30$15.00cache write $3.75Not published by the provider
40.2
Poor value (40.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
41 Β±8
Terse (41 Β±8). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
147.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.5
πŸ‡ΊπŸ‡Έ
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
129.7
From 442 benchmarks. Plenty of data behind it.
107Β Β±7
Coding IQ 107.2, 95% interval 101–114. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.00cache read $0.30$15.00cache write $3.75Not published by the provider
40.2
Poor value (40.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
41 Β±8
Terse (41 Β±8). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
147.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.5
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Sonnet 5.5We compared release dates and version names in our catalogue.
claude-sonnet-4-5-20250929 Β· 20250929
Inference by Anthropic
129.7
From 442 benchmarks. Plenty of data behind it.
107Β Β±7
Coding IQ 107.2, 95% interval 101–114. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.00cache read $0.30$15.00cache write $3.75Not published by the provider
40.2
Poor value (40.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
41 Β±8
Terse (41 Β±8). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
147.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude Sonnet 4.5
πŸ‡ΊπŸ‡Έ
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 Google
129.7
From 442 benchmarks. Plenty of data behind it.
107Β Β±7
Coding IQ 107.2, 95% interval 101–114. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.00cache read $0.30$15.00cache write $3.75Not published by the provider
40.2
Poor value (40.2). Costs more per task than its benchmark results predict. Plenty of data behind it.
41 Β±8
Terse (41 Β±8). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it.
147.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5
πŸ‡¨πŸ‡³
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.
129.7
From 306 benchmarks. Plenty of data behind it.
107Β Β±5
Coding IQ 106.7, 95% interval 102–112. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.573$2.58203K
49.7
Fair value (49.7). Costs per task about what its benchmark results predict. Plenty of data behind it.
55 Β±9
Typical (55 Β±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
146.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5
πŸ‡¨πŸ‡³
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 Alibaba Cloud
129.7
From 306 benchmarks. Plenty of data behind it.
107Β Β±5
Coding IQ 106.7, 95% interval 102–112. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.573$2.58Not published by the provider
49.7
Fair value (49.7). Costs per task about what its benchmark results predict. Plenty of data behind it.
55 Β±9
Typical (55 Β±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
146.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5
πŸ‡¨πŸ‡³
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 Nebius AI Studio
129.7
From 306 benchmarks. Plenty of data behind it.
107Β Β±5
Coding IQ 106.7, 95% interval 102–112. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.00$3.20Not published by the provider
49.7
Fair value (49.7). Costs per task about what its benchmark results predict. Plenty of data behind it.
55 Β±9
Typical (55 Β±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
146.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5
πŸ‡¨πŸ‡³
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 Novita AI
129.7
From 306 benchmarks. Plenty of data behind it.
107Β Β±5
Coding IQ 106.7, 95% interval 102–112. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.00cache read $0.20$3.20Not published by the provider
49.7
Fair value (49.7). Costs per task about what its benchmark results predict. Plenty of data behind it.
55 Β±9
Typical (55 Β±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
146.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5
πŸ‡¨πŸ‡³
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
129.7
From 306 benchmarks. Plenty of data behind it.
107Β Β±5
Coding IQ 106.7, 95% interval 102–112. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.00$3.20Not published by the provider
49.7
Fair value (49.7). Costs per task about what its benchmark results predict. Plenty of data behind it.
55 Β±9
Typical (55 Β±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
146.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GLM 5
πŸ‡¨πŸ‡³
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 Z.ai
129.7
From 306 benchmarks. Plenty of data behind it.
107Β Β±5
Coding IQ 106.7, 95% interval 102–112. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.00cache read $0.20$3.20Not published by the provider
49.7
Fair value (49.7). Costs per task about what its benchmark results predict. Plenty of data behind it.
55 Β±9
Typical (55 Β±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
146.5
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Mistral Large 4
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
129.6
From 173 benchmarks. Plenty of data behind it.
115Β Β±7
Coding IQ 114.7, 95% interval 108–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.36cache read $0.14$4.181M
30.8
Poor value (30.8). Costs more per task than its benchmark results predict. Plenty of data behind it.
62 Β±9
Chatty (62 Β±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.
154.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Mistral Large 4
πŸ‡«πŸ‡·
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
mistral-large-4-0
Inference by Mistral AI
129.6
From 173 benchmarks. Plenty of data behind it.
115Β Β±7
Coding IQ 114.7, 95% interval 108–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.36cache read $0.14$4.18Not published by the provider
30.8
Poor value (30.8). Costs more per task than its benchmark results predict. Plenty of data behind it.
62 Β±9
Chatty (62 Β±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.
154.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Qwen3.7 Plus
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
129.5
From 260 benchmarks. Plenty of data behind it.
109Β Β±6
Coding IQ 108.7, 95% interval 103–115. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.40cache read $0.08$1.60cache write $0.50984K
47.1
Poor value (47.1). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 Β±9
Chatty (59 Β±9). Generates more tokens than models with similar coding results. Measured with reasoning off. Little data behind it, so treat it as a rough estimate.
147.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Qwen3.7 Plus
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Inference by Alibaba Cloud
129.5
From 260 benchmarks. Plenty of data behind it.
109Β Β±6
Coding IQ 108.7, 95% interval 103–115. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.40cache read $0.08$1.60cache write $0.50Not published by the provider
47.1
Poor value (47.1). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 Β±9
Chatty (59 Β±9). Generates more tokens than models with similar coding results. Measured with reasoning off. Little data behind it, so treat it as a rough estimate.
147.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Qwen3.6 Plus
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Newer version
Newer versionQwen3.7 PlusWe compared release dates and version names in our catalogue.
129.4
From 256 benchmarks. Plenty of data behind it.
106Β Β±5
Coding IQ 105.7, 95% interval 101–110. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.50cache read $0.05$3.00cache write $0.625984K
38.6
Poor value (38.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
44 Β±12
Terse (44 Β±12). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
148.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Qwen3.6 Plus
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Newer version
Newer versionQwen3.7 PlusWe compared release dates and version names in our catalogue.
Inference by Alibaba Cloud
129.4
From 256 benchmarks. Plenty of data behind it.
106Β Β±5
Coding IQ 105.7, 95% interval 101–110. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.50cache read $0.05$3.00cache write $0.625Not published by the provider
38.6
Poor value (38.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
44 Β±12
Terse (44 Β±12). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
148.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Qwen 3.8 27B
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
129.4
From 251 benchmarks. Plenty of data behind it.
111Β Β±7
Coding IQ 111.4, 95% interval 104–119. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.08cache read $0.05$0.351M
39.7
Poor value (39.7). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
152.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Qwen 3.8 27B
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Inference by Alibaba Cloud
129.4
From 251 benchmarks. Plenty of data behind it.
111Β Β±7
Coding IQ 111.4, 95% interval 104–119. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.50cache read $0.10$3.00cache write $0.625Not published by the provider
39.7
Poor value (39.7). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
152.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Qwen 3.8 27B
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Inference by DeepInfra
129.4
From 251 benchmarks. Plenty of data behind it.
111Β Β±7
Coding IQ 111.4, 95% interval 104–119. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.20cache read $0.05$2.50Not published by the provider
39.7
Poor value (39.7). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
152.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Qwen 3.8 27B
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Inference by Novita AI
129.4
From 251 benchmarks. Plenty of data behind it.
111Β Β±7
Coding IQ 111.4, 95% interval 104–119. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.42cache read $0.085$3.00Not published by the provider
39.7
Poor value (39.7). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
152.6
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.20
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
grok-4-20-beta-0309-non-reasoning Β· beta+non-reasoning+0309
129.3
From 281 benchmarks. Plenty of data behind it.
108Β Β±8
Coding IQ 108.2, 95% interval 101–116. 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$6.002M
40.6
Poor value (40.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
45 Β±9
Typical (45 Β±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.
152.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.20
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
grok-4-20-beta-0309-reasoning Β· beta+reasoning+0309
129.3
From 281 benchmarks. Plenty of data behind it.
108Β Β±8
Coding IQ 108.2, 95% interval 101–116. 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$6.002M
40.6
Poor value (40.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
45 Β±9
Typical (45 Β±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.
152.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.20
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
grok-4-20-non-reasoning Β· non-reasoning
129.3
From 281 benchmarks. Plenty of data behind it.
108Β Β±8
Coding IQ 108.2, 95% interval 101–116. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.25cache read $0.20$2.502M
40.6
Poor value (40.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
45 Β±9
Typical (45 Β±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.
152.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.20
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
grok-4-20-reasoning Β· reasoning
129.3
From 281 benchmarks. Plenty of data behind it.
108Β Β±8
Coding IQ 108.2, 95% interval 101–116. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.25cache read $0.20$2.502M
40.6
Poor value (40.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
45 Β±9
Typical (45 Β±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.
152.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.20
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
grok-4.20-beta-0309-non-reasoning Β· beta+non-reasoning+0309
Inference by xAI
129.3
From 281 benchmarks. Plenty of data behind it.
108Β Β±8
Coding IQ 108.2, 95% interval 101–116. 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$6.00Not published by the provider
40.6
Poor value (40.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
45 Β±9
Typical (45 Β±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.
152.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Grok 4.20
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
grok-4.20-beta-0309-reasoning Β· beta+reasoning+0309
Inference by xAI
129.3
From 281 benchmarks. Plenty of data behind it.
108Β Β±8
Coding IQ 108.2, 95% interval 101–116. 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$6.00Not published by the provider
40.6
Poor value (40.6). Costs more per task than its benchmark results predict. Plenty of data behind it.
45 Β±9
Typical (45 Β±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.
152.3
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
DeepSeek V4 Flash
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Newer version
Newer versionDeepSeek V4.1 Flash 1017We compared release dates and version names in our catalogue.
129.1
From 229 benchmarks. Plenty of data behind it.
108Β Β±12
Coding IQ 107.8, 95% interval 95–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.076cache read $0.014$0.1531.1M
74.6
Good value (74.6). Cheaper per task than its benchmark results predict. Plenty of data behind it.
44 Β±9
Terse (44 Β±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
146.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
DeepSeek V4 Flash
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Newer version
Newer versionDeepSeek V4.1 Flash 1017We compared release dates and version names in our catalogue.
deepseek-v4-flash-0731
Inference by Alibaba Cloud
129.1
From 229 benchmarks. Plenty of data behind it.
108Β Β±12
Coding IQ 107.8, 95% interval 95–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.44cache read $0.044$1.32Not published by the provider
74.6
Good value (74.6). Cheaper per task than its benchmark results predict. Plenty of data behind it.
44 Β±9
Terse (44 Β±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
146.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
DeepSeek V4 Flash
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Newer version
Newer versionDeepSeek V4.1 Flash 1017We compared release dates and version names in our catalogue.
@cf/deepseek-ai/deepseek-v4-flash-0731
Inference by Cloudflare Workers AI
129.1
From 229 benchmarks. Plenty of data behind it.
108Β Β±12
Coding IQ 107.8, 95% interval 95–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.44cache read $0.014$1.32Not published by the provider
74.6
Good value (74.6). Cheaper per task than its benchmark results predict. Plenty of data behind it.
44 Β±9
Terse (44 Β±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
146.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
DeepSeek V4 Flash
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Newer version
Newer versionDeepSeek V4.1 Flash 1017We compared release dates and version names in our catalogue.
Inference by DeepInfra
129.1
From 229 benchmarks. Plenty of data behind it.
108Β Β±12
Coding IQ 107.8, 95% interval 95–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.09cache read $0.018$0.18Not published by the provider
74.6
Good value (74.6). Cheaper per task than its benchmark results predict. Plenty of data behind it.
44 Β±9
Terse (44 Β±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
146.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
DeepSeek V4 Flash
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Newer version
Newer versionDeepSeek V4.1 Flash 1017We compared release dates and version names in our catalogue.
Inference by DeepSeek
129.1
From 229 benchmarks. Plenty of data behind it.
108Β Β±12
Coding IQ 107.8, 95% interval 95–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.14cache read $0.0028$0.28Not published by the provider
74.6
Good value (74.6). Cheaper per task than its benchmark results predict. Plenty of data behind it.
44 Β±9
Terse (44 Β±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
146.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
DeepSeek V4 Flash
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Newer version
Newer versionDeepSeek V4.1 Flash 1017We compared release dates and version names in our catalogue.
accounts/fireworks/models/deepseek-v4-flash-0731
Inference by Fireworks AI
129.1
From 229 benchmarks. Plenty of data behind it.
108Β Β±12
Coding IQ 107.8, 95% interval 95–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.22cache read $0.007$0.66Not published by the provider
74.6
Good value (74.6). Cheaper per task than its benchmark results predict. Plenty of data behind it.
44 Β±9
Terse (44 Β±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
146.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
DeepSeek V4 Flash
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Newer version
Newer versionDeepSeek V4.1 Flash 1017We compared release dates and version names in our catalogue.
Inference by Inference Net
129.1
From 229 benchmarks. Plenty of data behind it.
108Β Β±12
Coding IQ 107.8, 95% interval 95–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.23cache read $0.0028$0.62Not published by the provider
74.6
Good value (74.6). Cheaper per task than its benchmark results predict. Plenty of data behind it.
44 Β±9
Terse (44 Β±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
146.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
DeepSeek V4 Flash
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Newer version
Newer versionDeepSeek V4.1 Flash 1017We compared release dates and version names in our catalogue.
deepseek/deepseek-v4-flash-0731
Inference by Novita AI
129.1
From 229 benchmarks. Plenty of data behind it.
108Β Β±12
Coding IQ 107.8, 95% interval 95–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.14cache read $0.028$0.28Not published by the provider
74.6
Good value (74.6). Cheaper per task than its benchmark results predict. Plenty of data behind it.
44 Β±9
Terse (44 Β±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
146.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
DeepSeek V4 Flash
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Newer version
Newer versionDeepSeek V4.1 Flash 1017We compared release dates and version names in our catalogue.
deepseek-ai/DeepSeek-V4-Flash-0731
Inference by Together AI
129.1
From 229 benchmarks. Plenty of data behind it.
108Β Β±12
Coding IQ 107.8, 95% interval 95–120. 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$0.28Not published by the provider
74.6
Good value (74.6). Cheaper per task than its benchmark results predict. Plenty of data behind it.
44 Β±9
Terse (44 Β±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
146.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Doubao Seed 2.0 Pro
Newer version
Newer versionDoubao Seed 2.1 ProWe compared release dates and version names in our catalogue.
seed-2-0-pro-260328 Β· 260328
129.0
From 86 benchmarks. Plenty of data behind it.
β‰ˆ 102Β Β±10
Coding IQ 101.6, 95% interval 92–112. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.50cache read $0.10$3.00262KNot enough data yetNot measuredNot measured
GPT-5.1 Codex
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-5.3 CodexWe compared the version names in our catalogue.
Inference by Microsoft Azure
129.0
From 31 benchmarks. Plenty of data behind it.
106Β Β±7
Coding IQ 106.2, 95% interval 99–113. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.25$10.00Not published by the provider
47.0
Poor value (47.0). Costs more per task than its benchmark results predict. A fair amount of data behind it.
54 Β±9
Typical (54 Β±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
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGPT-5.3 CodexWe compared the version names in our catalogue.
Inference by OpenAI
129.0
From 31 benchmarks. Plenty of data behind it.
106Β Β±7
Coding IQ 106.2, 95% interval 99–113. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.25$10.00Not published by the provider
47.0
Poor value (47.0). Costs more per task than its benchmark results predict. A fair amount of data behind it.
54 Β±9
Typical (54 Β±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
Grok Build 0.1
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
128.7
From 32 benchmarks. A fair amount of data behind it.
β‰ˆ 110Β Β±23
Coding IQ 109.5, 95% interval 87–133. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.00cache read $0.20$2.00256K
57.8
Good value (57.8). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Grok Build 0.1
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Inference by xAI
128.7
From 32 benchmarks. A fair amount of data behind it.
β‰ˆ 110Β Β±23
Coding IQ 109.5, 95% interval 87–133. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$1.00cache read $0.20$2.00Not published by the provider
57.8
Good value (57.8). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Kimi K2.5
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Newer version
Newer versionKimi K3.1We compared the version names in our catalogue.
128.5
From 401 benchmarks. Plenty of data behind it.
103Β Β±5
Coding IQ 102.9, 95% interval 98–108. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.574$3.011262K
48.2
Fair value (48.2). Costs per task about what its benchmark results predict. Plenty of data behind it.
42 Β±9
Terse (42 Β±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
148.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Kimi K2.5
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Newer version
Newer versionKimi K3.1We compared the version names in our catalogue.
Inference by Alibaba Cloud
128.5
From 401 benchmarks. Plenty of data behind it.
103Β Β±5
Coding IQ 102.9, 95% interval 98–108. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.574$3.011Not published by the provider
48.2
Fair value (48.2). Costs per task about what its benchmark results predict. Plenty of data behind it.
42 Β±9
Terse (42 Β±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
148.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Kimi K2.5
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Newer version
Newer versionKimi K3.1We compared the version names in our catalogue.
Inference by DeepInfra
128.5
From 401 benchmarks. Plenty of data behind it.
103Β Β±5
Coding IQ 102.9, 95% interval 98–108. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.45cache read $0.07$2.25Not published by the provider
48.2
Fair value (48.2). Costs per task about what its benchmark results predict. Plenty of data behind it.
42 Β±9
Terse (42 Β±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
148.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Kimi K2.5
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Newer version
Newer versionKimi K3.1We compared the version names in our catalogue.
Inference by Moonshot AI
128.5
From 401 benchmarks. Plenty of data behind it.
103Β Β±5
Coding IQ 102.9, 95% interval 98–108. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.60cache read $0.10$3.00Not published by the provider
48.2
Fair value (48.2). Costs per task about what its benchmark results predict. Plenty of data behind it.
42 Β±9
Terse (42 Β±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
148.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Kimi K2.5
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Newer version
Newer versionKimi K3.1We compared the version names in our catalogue.
Inference by Nebius AI Studio
128.5
From 401 benchmarks. Plenty of data behind it.
103Β Β±5
Coding IQ 102.9, 95% interval 98–108. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.50cache read $0.02$2.50Not published by the provider
48.2
Fair value (48.2). Costs per task about what its benchmark results predict. Plenty of data behind it.
42 Β±9
Terse (42 Β±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
148.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Kimi K2.5
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Newer version
Newer versionKimi K3.1We compared the version names in our catalogue.
Inference by Together AI
128.5
From 401 benchmarks. Plenty of data behind it.
103Β Β±5
Coding IQ 102.9, 95% interval 98–108. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.50$2.80Not published by the provider
48.2
Fair value (48.2). Costs per task about what its benchmark results predict. Plenty of data behind it.
42 Β±9
Terse (42 Β±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
148.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Qwen3.7 Flash
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Newer version
Newer versionQwen3.8 FlashWe compared release dates and version names in our catalogue.
128.4
From 15 benchmarks. A fair amount of data behind it.
Not enough data yet$0.03cache read $0.006$0.13cache write $0.0375984KNot enough data yetNot measuredNot measured
Qwen3.7 Flash
πŸ‡¨πŸ‡³
Maker headquartered in CN, according to the company's own website. The citation is on the model page.
Newer version
Newer versionQwen3.8 FlashWe compared release dates and version names in our catalogue.
Inference by Alibaba Cloud
128.4
From 15 benchmarks. A fair amount of data behind it.
Not enough data yet$0.03cache read $0.006$0.13cache write $0.0375Not published by the providerNot enough data yetNot measuredNot measured
Gemma 4 31B IT
πŸ‡ΊπŸ‡Έ
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.
128.3
From 333 benchmarks. Plenty of data behind it.
102Β Β±7
Coding IQ 101.7, 95% interval 94–109. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.10cache read $0.01$0.25262K
61.9
Good value (61.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
43 Β±9
Terse (43 Β±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
144.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Gemma 4 31B IT
πŸ‡ΊπŸ‡Έ
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.
gemma-4-31b
Inference by Cerebras
128.3
From 333 benchmarks. Plenty of data behind it.
102Β Β±7
Coding IQ 101.7, 95% interval 94–109. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.99$1.49Not published by the provider
61.9
Good value (61.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
43 Β±9
Terse (43 Β±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
144.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Gemma 4 31B IT
πŸ‡ΊπŸ‡Έ
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 DeepInfra
128.3
From 333 benchmarks. Plenty of data behind it.
102Β Β±7
Coding IQ 101.7, 95% interval 94–109. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.20$0.40Not published by the provider
61.9
Good value (61.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
43 Β±9
Terse (43 Β±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
144.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Gemma 4 31B IT
πŸ‡ΊπŸ‡Έ
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 Novita AI
128.3
From 333 benchmarks. Plenty of data behind it.
102Β Β±7
Coding IQ 101.7, 95% interval 94–109. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.14$0.40Not published by the provider
61.9
Good value (61.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
43 Β±9
Terse (43 Β±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
144.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Gemma 4 31B IT
πŸ‡ΊπŸ‡Έ
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
128.3
From 333 benchmarks. Plenty of data behind it.
102Β Β±7
Coding IQ 101.7, 95% interval 94–109. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.39$0.97Not published by the provider
61.9
Good value (61.9). Cheaper per task than its benchmark results predict. Plenty of data behind it.
43 Β±9
Terse (43 Β±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
144.1
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Muse Glimmer 30B
πŸ‡ΊπŸ‡Έ
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.
128.3
From 58 benchmarks. Plenty of data behind it.
Not enough data yet$0.30cache read $0.04$1.20131K
51.7
Fair value (51.7). Costs per task about what its benchmark results predict. A fair amount of data behind it.
Not measuredNot measured
Muse Glimmer 30B
πŸ‡ΊπŸ‡Έ
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 DeepInfra
128.3
From 58 benchmarks. Plenty of data behind it.
Not enough data yet$0.30cache read $0.04$1.20Not published by the provider
51.7
Fair value (51.7). Costs per task about what its benchmark results predict. A fair amount of data behind it.
Not measuredNot measured
Muse Glimmer 30B
πŸ‡ΊπŸ‡Έ
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
128.3
From 58 benchmarks. Plenty of data behind it.
Not enough data yet$0.35cache read $0.04$1.50Not published by the provider
51.7
Fair value (51.7). Costs per task about what its benchmark results predict. A fair amount of data behind it.
Not measuredNot measured
OpenAI o3
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
o3
Inference by Microsoft Azure
128.3
From 343 benchmarks. Plenty of data behind it.
100Β Β±6
Coding IQ 99.6, 95% interval 93–106. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.50$8.00Not published by the provider
54.5
Good value (54.5). Cheaper per task than its benchmark results predict. Plenty of data behind it.
58 Β±9
Chatty (58 Β±9). Generates more tokens than models with similar coding results. Measured at medium effort. A fair amount of data behind it.
147
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
OpenAI o3
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
o3
Inference by OpenAI
128.3
From 343 benchmarks. Plenty of data behind it.
100Β Β±6
Coding IQ 99.6, 95% interval 93–106. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00cache read $0.50$8.00Not published by the provider
54.5
Good value (54.5). Cheaper per task than its benchmark results predict. Plenty of data behind it.
58 Β±9
Chatty (58 Β±9). Generates more tokens than models with similar coding results. Measured at medium effort. A fair amount of data behind it.
147
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-5.4 mini
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
128.1
From 307 benchmarks. Plenty of data behind it.
104Β Β±5
Coding IQ 104.3, 95% interval 99–110. 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$4.50400K
39.8
Poor value (39.8). Costs more per task than its benchmark results predict. Plenty of data behind it.
46 Β±18
Typical (46 Β±18). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
149.4
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-5.4 mini
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Inference by Microsoft Azure
128.1
From 307 benchmarks. Plenty of data behind it.
104Β Β±5
Coding IQ 104.3, 95% interval 99–110. 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$4.50Not published by the provider
39.8
Poor value (39.8). Costs more per task than its benchmark results predict. Plenty of data behind it.
46 Β±18
Typical (46 Β±18). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
149.4
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
GPT-5.4 mini
πŸ‡ΊπŸ‡Έ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Inference by OpenAI
128.1
From 307 benchmarks. Plenty of data behind it.
104Β Β±5
Coding IQ 104.3, 95% interval 99–110. 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$4.50Not published by the provider
39.8
Poor value (39.8). Costs more per task than its benchmark results predict. Plenty of data behind it.
46 Β±18
Typical (46 Β±18). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
149.4
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API

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

How this data works