Listings
All listings: OpenRouter
Every listing for the models on page 5 of 26 of OpenRouter, including each model's other versions and routes. Back to OpenRouter
Sold by OpenRouter
99 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
- Epoch Capabilities Index
- Epoch Capabilities Index benchmark details
| Model | llminfo IQ | Coding IQ | Input $/1M | Output $/1M | Max Input Tokens | Value | Yap | Epoch Capabilities Index |
|---|---|---|---|---|---|---|---|---|
GPT-5.1 Codex 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 129.0From 31 benchmarks. Plenty of data behind it. | 106 ±7Coding 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. | $1.25cache read $0.13 | $10.00 | 400K | 47.0Poor value (47.0). Costs more per task than its benchmark results predict. A fair amount of data behind it. | 54 ±9Typical (54 ±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 Inference by Microsoft Azure🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 129.0From 31 benchmarks. Plenty of data behind it. | 106 ±7Coding 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. | $1.25cache read $0.13 | $10.00 | 272K | 47.0Poor value (47.0). Costs more per task than its benchmark results predict. A fair amount of data behind it. | 54 ±9Typical (54 ±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 |
Gemini 2.5 Pro 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 128.8From 374 benchmarks. Plenty of data behind it. | 101 ±18Coding IQ 100.6, 95% interval 83–118. 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 | $10.00 | 1M | 36.3Poor value (36.3). Costs more per task than its benchmark results predict. Plenty of data behind it. | 54 ±9Typical (54 ±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. | 144.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemini 2.5 Pro Inference by Google🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 128.8From 374 benchmarks. Plenty of data behind it. | 101 ±18Coding IQ 100.6, 95% interval 83–118. 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 | $10.00 | 1M | 36.3Poor value (36.3). Costs more per task than its benchmark results predict. Plenty of data behind it. | 54 ±9Typical (54 ±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. | 144.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemini 2.5 Pro Inference by Google🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 128.8From 374 benchmarks. Plenty of data behind it. | 101 ±18Coding IQ 100.6, 95% interval 83–118. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.625cache read $0.0625 | $5.00 | 1M | 36.3Poor value (36.3). Costs more per task than its benchmark results predict. Plenty of data behind it. | 54 ±9Typical (54 ±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. | 144.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemini 2.5 Pro Inference by Google🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 128.8From 374 benchmarks. Plenty of data behind it. | 101 ±18Coding IQ 100.6, 95% interval 83–118. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $2.25cache read $0.225 | $18.00 | 1M | 36.3Poor value (36.3). Costs more per task than its benchmark results predict. Plenty of data behind it. | 54 ±9Typical (54 ±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. | 144.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Grok Build 0.1 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 128.7From 32 benchmarks. A fair amount of data behind it. | ≈ 110 ±23Coding 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 | $2.00 | —Not published by the provider | 57.8Good value (57.8). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | —Not measured | —Not measured |
Doubao Seed 2.1 Turbobytedance-seed/seed-2-1-turbobytedance-seed/seed-2-1-turbo | 128.5From 60 benchmarks. Plenty of data behind it. | —Not enough data yet | $0.50 | $2.50 | 262K | —Not enough data yet | —Not measured | —Not measured |
Doubao Seed 2.1 Turbobytedance-seed/seed-2-1-turbo · fp8bytedance-seed/seed-2-1-turbo · fp8 Inference by Seed | 128.5From 60 benchmarks. Plenty of data behind it. | —Not enough data yet | $0.50 | $2.50 | 262K | —Not enough data yet | —Not measured | —Not measured |
Kimi K2.5 🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. Newer version | 128.5From 401 benchmarks. Plenty of data behind it. | 103 ±5Coding 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 $0.15 | $2.50 | 262K | 48.2Fair value (48.2). Costs per task about what its benchmark results predict. Plenty of data behind it. | 42 ±9Terse (42 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 148.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Kimi K2.5 Inference by Amazon Web Services🇨🇳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 | 128.5From 401 benchmarks. Plenty of data behind it. | 103 ±5Coding IQ 102.9, 95% interval 98–108. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.60 | $3.00 | 262K | 48.2Fair value (48.2). Costs per task about what its benchmark results predict. Plenty of data behind it. | 42 ±9Terse (42 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 148.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Kimi K2.5 Inference by Novita AI🇨🇳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 | 128.5From 401 benchmarks. Plenty of data behind it. | 103 ±5Coding 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. | $0.57cache read $0.095 | $2.85 | 262K | 48.2Fair value (48.2). Costs per task about what its benchmark results predict. Plenty of data behind it. | 42 ±9Terse (42 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 148.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Kimi K2.5 Inference by SiliconFlow🇨🇳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 | 128.5From 401 benchmarks. Plenty of data behind it. | 103 ±5Coding 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 $0.15 | $2.50 | 262K | 48.2Fair value (48.2). Costs per task about what its benchmark results predict. Plenty of data behind it. | 42 ±9Terse (42 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 148.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Qwen3.7 Flash 🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. Newer version | 128.4From 15 benchmarks. A fair amount of data behind it. | —Not enough data yet | $0.03cache read $0.006 | $0.13cache write $0.038 | 1M | —Not enough data yet | —Not measured | —Not measured |
Qwen3.7 Flash Inference by Alibaba Cloud🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. Newer version | 128.4From 15 benchmarks. A fair amount of data behind it. | —Not enough data yet | $0.03cache read $0.006 | $0.13cache write $0.038 | 984K | —Not enough data yet | —Not measured | —Not measured |
Claude Opus 4.1 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 128.3From 249 benchmarks. Plenty of data behind it. | 109 ±7Coding IQ 108.6, 95% interval 102–115. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $15.00cache read $1.50 | $75.00cache write $18.75 | 200K | 34.6Poor value (34.6). Costs more per task than its benchmark results predict. Plenty of data behind it. | 35 ±9Terse (35 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 144.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Claude Opus 4.1 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 128.3From 249 benchmarks. Plenty of data behind it. | 109 ±7Coding IQ 108.6, 95% interval 102–115. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $7.50cache read $0.75 | $37.50cache write $9.375 | 200K | 34.6Poor value (34.6). Costs more per task than its benchmark results predict. Plenty of data behind it. | 35 ±9Terse (35 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 144.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Claude Opus 4.1 Inference by Amazon Web Services🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 128.3From 249 benchmarks. Plenty of data behind it. | 109 ±7Coding IQ 108.6, 95% interval 102–115. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $15.00cache read $1.50 | $75.00cache write $18.75 | 200K | 34.6Poor value (34.6). Costs more per task than its benchmark results predict. Plenty of data behind it. | 35 ±9Terse (35 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 144.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 4 31B IT 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 128.3From 333 benchmarks. Plenty of data behind it. | 102 ±7Coding 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. | $0.20cache read $0.09 | $0.40 | 262K | 61.9Good value (61.9). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 43 ±9Terse (43 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 144.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 4 31B IT 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 128.3From 333 benchmarks. Plenty of data behind it. | 102 ±7Coding 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. | $0.00 | $0.00 | 262K | 61.9Good value (61.9). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 43 ±9Terse (43 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 144.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 4 31B IT Inference by Chutes🇺🇸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. | 128.3From 333 benchmarks. Plenty of data behind it. | 102 ±7Coding 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. | $0.12cache read $0.012 | $0.37 | 131K | 61.9Good value (61.9). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 43 ±9Terse (43 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 144.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 4 31B IT Inference by Coreweave🇺🇸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. | 128.3From 333 benchmarks. Plenty of data behind it. | 102 ±7Coding 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. | $0.10 | $0.34 | 262K | 61.9Good value (61.9). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 43 ±9Terse (43 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 144.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 4 31B IT Inference by Crusoe🇺🇸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. | 128.3From 333 benchmarks. Plenty of data behind it. | 102 ±7Coding 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 | $0.40 | 262K | 61.9Good value (61.9). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 43 ±9Terse (43 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 144.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 4 31B IT Inference by DeepInfra🇺🇸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. | 128.3From 333 benchmarks. Plenty of data behind it. | 102 ±7Coding 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 | $0.40 | 262K | 61.9Good value (61.9). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 43 ±9Terse (43 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 144.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 4 31B IT Inference by DeepInfra🇺🇸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. | 128.3From 333 benchmarks. Plenty of data behind it. | 102 ±7Coding 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. | $0.16 | $0.32 | 262K | 61.9Good value (61.9). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 43 ±9Terse (43 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 144.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 4 31B IT Inference by DeepInfra🇺🇸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. | 128.3From 333 benchmarks. Plenty of data behind it. | 102 ±7Coding 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. | $0.30 | $0.60 | 262K | 61.9Good value (61.9). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 43 ±9Terse (43 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 144.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 4 31B IT Inference by Friendli AI🇺🇸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. | 128.3From 333 benchmarks. Plenty of data behind it. | 102 ±7Coding 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 | $0.40 | 262K | 61.9Good value (61.9). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 43 ±9Terse (43 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 144.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 4 31B IT Inference by Google🇺🇸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. | 128.3From 333 benchmarks. Plenty of data behind it. | 102 ±7Coding 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. | $0.00 | $0.00 | 262K | 61.9Good value (61.9). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 43 ±9Terse (43 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 144.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 4 31B IT Inference by Kt🇺🇸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. | 128.3From 333 benchmarks. Plenty of data behind it. | 102 ±7Coding 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. | $0.10 | $0.34 | 262K | 61.9Good value (61.9). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 43 ±9Terse (43 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 144.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 4 31B IT Inference by Modal🇺🇸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. | 128.3From 333 benchmarks. Plenty of data behind it. | 102 ±7Coding 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. | $0.34cache read $0.10 | $0.10 | 131K | 61.9Good value (61.9). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 43 ±9Terse (43 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 144.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 4 31B IT Inference by Modelrun🇺🇸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. | 128.3From 333 benchmarks. Plenty of data behind it. | 102 ±7Coding 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. | $0.75cache read $0.20 | $1.00 | 262K | 61.9Good value (61.9). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 43 ±9Terse (43 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 144.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 4 31B IT Inference by Nextbit🇺🇸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. | 128.3From 333 benchmarks. Plenty of data behind it. | 102 ±7Coding 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. | $0.125cache read $0.075 | $0.34 | 262K | 61.9Good value (61.9). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 43 ±9Terse (43 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 144.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 4 31B IT Inference by Novita AI🇺🇸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. | 128.3From 333 benchmarks. Plenty of data behind it. | 102 ±7Coding 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 | $0.40 | 262K | 61.9Good value (61.9). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 43 ±9Terse (43 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 144.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 4 31B IT Inference by Parasail🇺🇸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. | 128.3From 333 benchmarks. Plenty of data behind it. | 102 ±7Coding 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. | $0.15cache read $0.06 | $0.40 | 262K | 61.9Good value (61.9). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 43 ±9Terse (43 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 144.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 4 31B IT Inference by Primeintellect🇺🇸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. | 128.3From 333 benchmarks. Plenty of data behind it. | 102 ±7Coding 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. | $0.151cache read $0.076 | $0.253 | 262K | 61.9Good value (61.9). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 43 ±9Terse (43 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 144.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 4 31B IT Inference by SambaNova🇺🇸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. | 128.3From 333 benchmarks. Plenty of data behind it. | 102 ±7Coding 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. | $0.38 | $1.15 | 131K | 61.9Good value (61.9). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 43 ±9Terse (43 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 144.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 4 31B IT Inference by SiliconFlow🇺🇸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. | 128.3From 333 benchmarks. Plenty of data behind it. | 102 ±7Coding 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. | $0.75cache read $0.25 | $1.00 | 262K | 61.9Good value (61.9). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 43 ±9Terse (43 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 144.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 4 31B IT Inference by Venice🇺🇸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. | 128.3From 333 benchmarks. Plenty of data behind it. | 102 ±7Coding 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. | $0.12cache read $0.09 | $0.36 | 256K | 61.9Good value (61.9). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 43 ±9Terse (43 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 144.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Muse Glimmer 30B 🇺🇸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. | 128.3From 58 benchmarks. Plenty of data behind it. | —Not enough data yet | $0.35cache read $0.04 | $1.50 | 131K | 51.7Fair value (51.7). Costs per task about what its benchmark results predict. A fair amount of data behind it. | —Not measured | —Not measured |
Muse Glimmer 30B 🇺🇸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. | 128.3From 58 benchmarks. Plenty of data behind it. | —Not enough data yet | $0.24cache read $0.032 | $0.96 | 131K | 51.7Fair value (51.7). Costs per task about what its benchmark results predict. A fair amount of data behind it. | —Not measured | —Not measured |
Muse Glimmer 30B Inference by DeepInfra🇺🇸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. | 128.3From 58 benchmarks. Plenty of data behind it. | —Not enough data yet | $0.24cache read $0.032 | $0.96 | 131K | 51.7Fair value (51.7). Costs per task about what its benchmark results predict. A fair amount of data behind it. | —Not measured | —Not measured |
Muse Glimmer 30B Inference by DeepInfra🇺🇸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. | 128.3From 58 benchmarks. Plenty of data behind it. | —Not enough data yet | $0.30cache read $0.04 | $1.20 | 131K | 51.7Fair value (51.7). Costs per task about what its benchmark results predict. A fair amount of data behind it. | —Not measured | —Not measured |
Muse Glimmer 30B Inference by Modelrun🇺🇸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. | 128.3From 58 benchmarks. Plenty of data behind it. | —Not enough data yet | $0.30cache read $0.04 | $1.20 | 131K | 51.7Fair value (51.7). Costs per task about what its benchmark results predict. A fair amount of data behind it. | —Not measured | —Not measured |
Muse Glimmer 30B Inference by Together AI🇺🇸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. | 128.3From 58 benchmarks. Plenty of data behind it. | —Not enough data yet | $0.35cache read $0.04 | $1.50 | 131K | 51.7Fair value (51.7). Costs per task about what its benchmark results predict. A fair amount of data behind it. | —Not measured | —Not measured |
OpenAI o3 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 128.3From 343 benchmarks. Plenty of data behind it. | 100 ±6Coding 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 | $8.00 | 200K | 54.5Good value (54.5). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 58 ±9Chatty (58 ±9). Generates more tokens than models with similar coding results. Measured at medium effort. A fair amount of data behind it. | 147Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
OpenAI o3 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 128.3From 343 benchmarks. Plenty of data behind it. | 100 ±6Coding 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. | $1.00cache read $0.25 | $4.00 | 200K | 54.5Good value (54.5). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 58 ±9Chatty (58 ±9). Generates more tokens than models with similar coding results. Measured at medium effort. A fair amount of data behind it. | 147Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
OpenAI o3 Inference by OpenAI🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 128.3From 343 benchmarks. Plenty of data behind it. | 100 ±6Coding 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 | $8.00 | 200K | 54.5Good value (54.5). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 58 ±9Chatty (58 ±9). Generates more tokens than models with similar coding results. Measured at medium effort. A fair amount of data behind it. | 147Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-5.4 mini 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 128.1From 307 benchmarks. Plenty of data behind it. | 104 ±5Coding 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 | $4.50 | 400K | 39.8Poor value (39.8). Costs more per task than its benchmark results predict. Plenty of data behind it. | 46 ±18Typical (46 ±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. | 149.4Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-5.4 mini 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 128.1From 307 benchmarks. Plenty of data behind it. | 104 ±5Coding 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. | $0.375cache read $0.0375 | $2.25 | 400K | 39.8Poor value (39.8). Costs more per task than its benchmark results predict. Plenty of data behind it. | 46 ±18Typical (46 ±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. | 149.4Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-5.4 mini Inference by Microsoft Azure🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 128.1From 307 benchmarks. Plenty of data behind it. | 104 ±5Coding 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 | $4.50 | 400K | 39.8Poor value (39.8). Costs more per task than its benchmark results predict. Plenty of data behind it. | 46 ±18Typical (46 ±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. | 149.4Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-5.4 mini Inference by OpenAI🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 128.1From 307 benchmarks. Plenty of data behind it. | 104 ±5Coding 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 | $4.50 | 400K | 39.8Poor value (39.8). Costs more per task than its benchmark results predict. Plenty of data behind it. | 46 ±18Typical (46 ±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. | 149.4Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-5.4 mini Inference by OpenAI🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 128.1From 307 benchmarks. Plenty of data behind it. | 104 ±5Coding 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. | $1.50cache read $0.15 | $9.00 | 400K | 39.8Poor value (39.8). Costs more per task than its benchmark results predict. Plenty of data behind it. | 46 ±18Typical (46 ±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. | 149.4Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-5.4 mini Inference by OpenAI🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 128.1From 307 benchmarks. Plenty of data behind it. | 104 ±5Coding 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. | $0.375cache read $0.0375 | $2.25 | 400K | 39.8Poor value (39.8). Costs more per task than its benchmark results predict. Plenty of data behind it. | 46 ±18Typical (46 ±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. | 149.4Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
MiMo V2.5 Pro 🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. Newer version | 128.0From 172 benchmarks. Plenty of data behind it. | 107 ±6Coding IQ 106.5, 95% interval 101–112. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.48cache read $0.096 | $1.80 | 262K | 59.5Good value (59.5). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 55 ±9Typical (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. | —Not measured |
MiMo V2.5 Pro Inference by Digitalocean🇨🇳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 | 128.0From 172 benchmarks. Plenty of data behind it. | 107 ±6Coding IQ 106.5, 95% interval 101–112. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.48cache read $0.096 | $1.80 | 262K | 59.5Good value (59.5). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 55 ±9Typical (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. | —Not measured |
GPT-5 Codex 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 127.7From 21 benchmarks. Plenty of data behind it. | ≈ 106 ±9staleCoding IQ 106.4, 95% interval 98–115. 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. Its newest result is over a year old. | $1.25 | $10.00 | —Not published by the provider | 49.4Fair value (49.4). Costs per task about what its benchmark results predict. A fair amount of data behind it. | —Not measured | —Not measured |
Gemini 3.5 Flash Lite 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 127.5From 169 benchmarks. Plenty of data behind it. | 105 ±6Coding IQ 105.2, 95% interval 99–111. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.30cache read $0.03 | $2.50 | 1M | 46.2Poor value (46.2). Costs more per task than its benchmark results predict. Plenty of data behind it. | 50 ±9Typical (50 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 145.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemini 3.5 Flash Lite 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 127.5From 169 benchmarks. Plenty of data behind it. | 105 ±6Coding IQ 105.2, 95% interval 99–111. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.15cache read $0.015 | $1.25 | 1M | 46.2Poor value (46.2). Costs more per task than its benchmark results predict. Plenty of data behind it. | 50 ±9Typical (50 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 145.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemini 3.5 Flash Lite Inference by Google🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 127.5From 169 benchmarks. Plenty of data behind it. | 105 ±6Coding IQ 105.2, 95% interval 99–111. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.30cache read $0.03 | $2.50 | 1M | 46.2Poor value (46.2). Costs more per task than its benchmark results predict. Plenty of data behind it. | 50 ±9Typical (50 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 145.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemini 3.5 Flash Lite Inference by Google🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 127.5From 169 benchmarks. Plenty of data behind it. | 105 ±6Coding IQ 105.2, 95% interval 99–111. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.15cache read $0.015 | $1.25 | 1M | 46.2Poor value (46.2). Costs more per task than its benchmark results predict. Plenty of data behind it. | 50 ±9Typical (50 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 145.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemini 3.5 Flash Lite Inference by Google🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 127.5From 169 benchmarks. Plenty of data behind it. | 105 ±6Coding IQ 105.2, 95% interval 99–111. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.15cache read $0.015 | $1.25 | 1M | 46.2Poor value (46.2). Costs more per task than its benchmark results predict. Plenty of data behind it. | 50 ±9Typical (50 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 145.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemini 3.5 Flash Lite Inference by Google🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 127.5From 169 benchmarks. Plenty of data behind it. | 105 ±6Coding IQ 105.2, 95% interval 99–111. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.30cache read $0.03 | $2.50 | 1M | 46.2Poor value (46.2). Costs more per task than its benchmark results predict. Plenty of data behind it. | 50 ±9Typical (50 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 145.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemini 3.5 Flash Lite Inference by Google🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 127.5From 169 benchmarks. Plenty of data behind it. | 105 ±6Coding IQ 105.2, 95% interval 99–111. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.15cache read $0.015 | $1.25 | 1M | 46.2Poor value (46.2). Costs more per task than its benchmark results predict. Plenty of data behind it. | 50 ±9Typical (50 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 145.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemini 3.5 Flash Lite Inference by Google🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 127.5From 169 benchmarks. Plenty of data behind it. | 105 ±6Coding IQ 105.2, 95% interval 99–111. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.54cache read $0.054 | $4.50 | 1M | 46.2Poor value (46.2). Costs more per task than its benchmark results predict. Plenty of data behind it. | 50 ±9Typical (50 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 145.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemini 3.5 Flash Lite Inference by Google🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 127.5From 169 benchmarks. Plenty of data behind it. | 105 ±6Coding IQ 105.2, 95% interval 99–111. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.54cache read $0.054 | $4.50 | 1M | 46.2Poor value (46.2). Costs more per task than its benchmark results predict. Plenty of data behind it. | 50 ±9Typical (50 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 145.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Claude Opus 4 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 127.4From 296 benchmarks. Plenty of data behind it. | 102 ±6Coding IQ 102.3, 95% interval 96–109. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $15.00cache read $1.50 | $75.00cache write $18.75 | —Not published by the provider | 26.0Poor value (26.0). Costs more per task than its benchmark results predict. Plenty of data behind it. | 43 ±9Terse (43 ±9). Generates fewer tokens than models with similar coding results. Measured at high effort. Little data behind it, so treat it as a rough estimate. | 142.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Inkling Small 🇺🇸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. | 127.4From 169 benchmarks. Plenty of data behind it. | 107 ±7Coding IQ 107.0, 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. | $0.45cache read $0.10 | $1.20 | 524K | 45.5Poor value (45.5). Costs more per task than its benchmark results predict. Plenty of data behind it. | 42 ±9Terse (42 ±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. | 150.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Inkling Small 🇺🇸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. | 127.4From 169 benchmarks. Plenty of data behind it. | 107 ±7Coding IQ 107.0, 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. | $0.36cache read $0.08 | $0.96 | 524K | 45.5Poor value (45.5). Costs more per task than its benchmark results predict. Plenty of data behind it. | 42 ±9Terse (42 ±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. | 150.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Inkling Small Inference by DeepInfra🇺🇸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. | 127.4From 169 benchmarks. Plenty of data behind it. | 107 ±7Coding IQ 107.0, 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. | $0.36cache read $0.08 | $0.96 | 524K | 45.5Poor value (45.5). Costs more per task than its benchmark results predict. Plenty of data behind it. | 42 ±9Terse (42 ±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. | 150.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Inkling Small Inference by DeepInfra🇺🇸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. | 127.4From 169 benchmarks. Plenty of data behind it. | 107 ±7Coding IQ 107.0, 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. | $0.45cache read $0.10 | $1.20 | 524K | 45.5Poor value (45.5). Costs more per task than its benchmark results predict. Plenty of data behind it. | 42 ±9Terse (42 ±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. | 150.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemini 2.5 Pro Preview 05-06 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 127.2From 100 benchmarks. Plenty of data behind it. | —Not enough data yet | $1.25 | $10.00 | —Not published by the provider | 59.8Good value (59.8). Cheaper per task than its benchmark results predict. A fair amount of data behind it. | —Not measured | —Not measured |
Hy3 (Deep Infra) 🇨🇳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. | 127.2From 119 benchmarks. Plenty of data behind it. | 111 ±6Coding IQ 111.3, 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. | $0.14cache read $0.035 | $0.58 | 262K | 52.3Fair value (52.3). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. | —Not measured | —Not measured |
Hy3 (Deep Infra) Inference by Novita AI🇨🇳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. | 127.2From 119 benchmarks. Plenty of data behind it. | 111 ±6Coding IQ 111.3, 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. | $0.14cache read $0.035 | $0.58 | 262K | 52.3Fair value (52.3). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. | —Not measured | —Not measured |
Hy3 (Deep Infra) Inference by Tencent🇨🇳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. | 127.2From 119 benchmarks. Plenty of data behind it. | 111 ±6Coding IQ 111.3, 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. | $0.132cache read $0.033 | $0.528 | 262K | 52.3Fair value (52.3). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. | —Not measured | —Not measured |
Gemini 2.5 Pro Preview 03-25 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 127.1From 128 benchmarks. Plenty of data behind it. | —Not enough data yet | $1.25 | $10.00 | —Not published by the provider | 51.8Fair value (51.8). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. | —Not measured | —Not measured |
Claude Sonnet 4 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 127.0From 321 benchmarks. Plenty of data behind it. | 99 ±7Coding IQ 99.2, 95% interval 92–106. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $3.00cache read $0.30 | $15.00cache write $3.75 | —Not published by the provider | 42.3Poor value (42.3). Costs more per task than its benchmark results predict. Plenty of data behind it. | 47 ±9Typical (47 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 141.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GLM 4.7 🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. Newer version | 127.0From 234 benchmarks. Plenty of data behind it. | 104 ±5Coding IQ 103.5, 95% interval 98–109. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.40cache read $0.08 | $1.75 | 203K | 41.0Poor value (41.0). Costs more per task than its benchmark results predict. Plenty of data behind it. | 61 ±9Chatty (61 ±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 143.3Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GLM 4.7 Inference by DeepInfra🇨🇳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 | 127.0From 234 benchmarks. Plenty of data behind it. | 104 ±5Coding IQ 103.5, 95% interval 98–109. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.40cache read $0.08 | $1.75 | 203K | 41.0Poor value (41.0). Costs more per task than its benchmark results predict. Plenty of data behind it. | 61 ±9Chatty (61 ±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 143.3Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GLM 4.7 Inference by DeepInfra🇨🇳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 | 127.0From 234 benchmarks. Plenty of data behind it. | 104 ±5Coding IQ 103.5, 95% interval 98–109. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.32cache read $0.064 | $1.40 | 203K | 41.0Poor value (41.0). Costs more per task than its benchmark results predict. Plenty of data behind it. | 61 ±9Chatty (61 ±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 143.3Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GLM 4.7 Inference by Mancer 2🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. Newer version | 127.0From 234 benchmarks. Plenty of data behind it. | 104 ±5Coding IQ 103.5, 95% interval 98–109. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.70cache read $0.35 | $2.50 | 131K | 41.0Poor value (41.0). Costs more per task than its benchmark results predict. Plenty of data behind it. | 61 ±9Chatty (61 ±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 143.3Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GLM 4.7 Inference by Novita AI🇨🇳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 | 127.0From 234 benchmarks. Plenty of data behind it. | 104 ±5Coding IQ 103.5, 95% interval 98–109. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.60cache read $0.11 | $2.20 | 205K | 41.0Poor value (41.0). Costs more per task than its benchmark results predict. Plenty of data behind it. | 61 ±9Chatty (61 ±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 143.3Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GLM 4.7 Inference by Venice🇨🇳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 | 127.0From 234 benchmarks. Plenty of data behind it. | 104 ±5Coding IQ 103.5, 95% interval 98–109. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.4004cache read $0.0801 | $1.9292 | 198K | 41.0Poor value (41.0). Costs more per task than its benchmark results predict. Plenty of data behind it. | 61 ±9Chatty (61 ±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 143.3Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GLM 4.7 Inference by Z.ai🇨🇳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 | 127.0From 234 benchmarks. Plenty of data behind it. | 104 ±5Coding IQ 103.5, 95% interval 98–109. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.60cache read $0.11 | $2.20 | 203K | 41.0Poor value (41.0). Costs more per task than its benchmark results predict. Plenty of data behind it. | 61 ±9Chatty (61 ±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 143.3Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
MiMo V2.5 🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 127.0From 145 benchmarks. Plenty of data behind it. | 108 ±6Coding IQ 107.8, 95% interval 102–114. 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 | $2.00 | 1M | 59.9Good value (59.9). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 55 ±9Typical (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. | —Not measured |
MiMo V2.5 Inference by Venice🇨🇳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. | 127.0From 145 benchmarks. Plenty of data behind it. | 108 ±6Coding IQ 107.8, 95% interval 102–114. 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 | $2.00 | 1M | 59.9Good value (59.9). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 55 ±9Typical (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. | —Not measured |
Inkling FP4 🇺🇸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. | 126.9From 215 benchmarks. Plenty of data behind it. | 102 ±6Coding IQ 101.9, 95% interval 96–107. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.00cache read $0.17 | $4.05 | 524K | 27.9Poor value (27.9). Costs more per task than its benchmark results predict. Plenty of data behind it. | 58 ±9Chatty (58 ±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. | 148.4Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Inkling FP4 Inference by Together AI🇺🇸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. | 126.9From 215 benchmarks. Plenty of data behind it. | 102 ±6Coding IQ 101.9, 95% interval 96–107. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.00cache read $0.17 | $4.05 | 524K | 27.9Poor value (27.9). Costs more per task than its benchmark results predict. Plenty of data behind it. | 58 ±9Chatty (58 ±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. | 148.4Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Kimi K2.7 Code 🇨🇳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. | 126.9From 102 benchmarks. Plenty of data behind it. | 105 ±9Coding IQ 104.5, 95% interval 96–113. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.60cache read $0.12 | $3.00 | 262K | 43.6Poor value (43.6). Costs more per task than its benchmark results predict. Plenty of data behind it. | 62 ±9Chatty (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. | 151.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Kimi K2.7 Code Inference by Alibaba Cloud🇨🇳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. | 126.9From 102 benchmarks. Plenty of data behind it. | 105 ±9Coding IQ 104.5, 95% interval 96–113. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.95cache read $0.19 | $4.00 | 229K | 43.6Poor value (43.6). Costs more per task than its benchmark results predict. Plenty of data behind it. | 62 ±9Chatty (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. | 151.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Kimi K2.7 Code Inference by Coreweave🇨🇳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. | 126.9From 102 benchmarks. Plenty of data behind it. | 105 ±9Coding IQ 104.5, 95% interval 96–113. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.60cache read $0.12 | $3.00 | 262K | 43.6Poor value (43.6). Costs more per task than its benchmark results predict. Plenty of data behind it. | 62 ±9Chatty (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. | 151.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Kimi K2.7 Code Inference by Inceptron🇨🇳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. | 126.9From 102 benchmarks. Plenty of data behind it. | 105 ±9Coding IQ 104.5, 95% interval 96–113. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.61cache read $0.17 | $3.55 | 262K | 43.6Poor value (43.6). Costs more per task than its benchmark results predict. Plenty of data behind it. | 62 ±9Chatty (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. | 151.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Kimi K2.7 Code Inference by Moonshot AI🇨🇳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. | 126.9From 102 benchmarks. Plenty of data behind it. | 105 ±9Coding IQ 104.5, 95% interval 96–113. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.95cache read $0.19 | $4.00 | 262K | 43.6Poor value (43.6). Costs more per task than its benchmark results predict. Plenty of data behind it. | 62 ±9Chatty (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. | 151.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Kimi K2.7 Code Inference by Moonshot AI🇨🇳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. | 126.9From 102 benchmarks. Plenty of data behind it. | 105 ±9Coding IQ 104.5, 95% interval 96–113. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.90cache read $0.38 | $8.00 | 262K | 43.6Poor value (43.6). Costs more per task than its benchmark results predict. Plenty of data behind it. | 62 ±9Chatty (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. | 151.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Kimi K2.7 Code Inference by Novita AI🇨🇳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. | 126.9From 102 benchmarks. Plenty of data behind it. | 105 ±9Coding IQ 104.5, 95% interval 96–113. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.912cache read $0.1824 | $3.84 | 262K | 43.6Poor value (43.6). Costs more per task than its benchmark results predict. Plenty of data behind it. | 62 ±9Chatty (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. | 151.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Kimi K2.7 Code Inference by SiliconFlow🇨🇳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. | 126.9From 102 benchmarks. Plenty of data behind it. | 105 ±9Coding IQ 104.5, 95% interval 96–113. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.8592cache read $0.1799 | $3.80 | 262K | 43.6Poor value (43.6). Costs more per task than its benchmark results predict. Plenty of data behind it. | 62 ±9Chatty (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. | 151.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Kimi K2.7 Code Inference by Streamlake🇨🇳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. | 126.9From 102 benchmarks. Plenty of data behind it. | 105 ±9Coding IQ 104.5, 95% interval 96–113. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.7125cache read $0.1425 | $3.00 | 256K | 43.6Poor value (43.6). Costs more per task than its benchmark results predict. Plenty of data behind it. | 62 ±9Chatty (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. | 151.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Kimi K2.7 Code Inference by Venice🇨🇳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. | 126.9From 102 benchmarks. Plenty of data behind it. | 105 ±9Coding IQ 104.5, 95% interval 96–113. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.75cache read $0.16 | $3.50 | 256K | 43.6Poor value (43.6). Costs more per task than its benchmark results predict. Plenty of data behind it. | 62 ±9Chatty (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. | 151.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GLM 5 Turbo 🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 126.8From 54 benchmarks. A fair amount of data behind it. | ≈ 104 ±11Coding IQ 103.5, 95% interval 93–114. 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. | $1.20cache read $0.24 | $4.00 | 203K | 48.2Fair value (48.2). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. | —Not measured | —Not measured |
GLM 5 Turbo Inference by Z.ai🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 126.8From 54 benchmarks. A fair amount of data behind it. | ≈ 104 ±11Coding IQ 103.5, 95% interval 93–114. 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. | $1.20cache read $0.24 | $4.00 | 203K | 48.2Fair value (48.2). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. | —Not measured | —Not measured |
Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence)