Every model. Every benchmark. One table.
Curated catalog with lineage and sourced scores.
106 models · 6 benchmarks
columns
| ↗ | ↗ | ↗ | ↗ | ↗ | ↗ | |||||
|---|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 5 | 100 | $5 | $25 | — | — | — | — | 96 | — | |
| GPT-5.6 | 100 | $5 | $30 | — | — | 94.6 | — | — | — | |
| Claude Mythos 5 | 97 | $10 | $50 | — | — | 94.1 | — | 95.5 | — | |
| Claude Fable 5 | 96 | $10 | $50 | — | — | — | — | 95 | — | |
| Claude Opus 4.7 | 94 | $5 | $25 | — | — | 94.2 | — | 87.6 | — | |
| GPT-5.5 | 94 | $5 | $30 | — | — | 93.6 | — | — | — | |
| Claude Opus 4.8 | 93 | $5 | $25 | — | — | 93.6 | — | 88.6 | — | |
| Gemini 3.1 Pro | 91 | $2 | $12 | — | — | 94.3 | — | 80.6 | — | |
| GPT-5.4 | 90 | $2.5 | $15 | — | — | 92.8 | — | — | — | |
| Claude Sonnet 5 | 90 | $3 | $15 | — | — | — | — | 85.2 | — | |
| Claude Opus 4.6 | 89 | $5 | $25 | — | — | 91.31 | 99.79 | 80.84 | — | |
| GPT-5.2 | 88 | $1.75 | $14 | — | — | 92.4 | 100 | 80 | — | |
| DeepSeek V4-Pro | 85 | $0.435 | $0.87 | — | 87.5 | 90.1 | — | 80.6 | — | |
| GLM-5.2 | 84 | $1.4 | $4.4 | — | — | 91.2 | — | — | — | |
| Kimi K2.6 | 80 | $0.95 | $4 | — | — | 90.5 | — | 80.2 | — | |
| MiniMax M3 | 79 | $0.3 | $1.2 | — | — | — | — | 80.5 | — | |
| Claude Sonnet 4.6 | 79 | $3 | $15 | — | — | 89.9 | 95.6 | 79.6 | — | |
| Kimi K2.5 | 78 | $0.6 | $3 | — | 87.1 | 87.6 | 96.1 | 76.8 | — | |
| Claude Opus 4.5 | 77 | $5 | $25 | — | — | 87 | 92.77 | 80.9 | — | |
| Qwen3.5 397B A17B | 76 | $0.6 | $3.6 | — | 87.8 | 88.4 | — | 76.4 | — | |
| DeepSeek V4-Flash | 76 | $0.14 | $0.28 | — | 86.2 | 88.1 | — | 79 | — | |
| Gemini 3 Flash | 75 | $0.5 | $3 | — | — | 90.4 | — | 78 | — | |
| Mistral Large 2 | 73 | self-host | self-host | 84 | — | — | — | — | 92 | |
| Gemma 4 31B Instruct | 70 | self-host | self-host | — | 85.2 | 84.3 | — | — | — | |
| Gemini 3 Pro | 70 | — | — | — | — | 91.9 | — | 76.2 | — | |
| GPT-5.1 | 69 | $1.25 | $10 | — | — | 88.1 | 94 | 76.3 | — | |
| Gemini 3.1 Flash-Lite | 68 | $0.25 | $1.5 | — | — | 86.9 | — | — | — | |
| GPT-5.1-Codex-Max | 67 | $1.25 | $10 | — | — | — | — | 77.9 | — | |
| GPT-5 | 66 | $1.25 | $10 | — | — | — | 94.6 | 74.9 | — | |
| GLM-4.7 | 66 | $0.6 | $2.2 | — | 84.3 | 85.7 | 95.7 | 73.8 | — | |
| GLM-5.1 | 65 | $1.4 | $4.4 | — | — | 86.2 | — | — | — | |
| GLM-5 | 64 | $1 | $3.2 | — | — | 86 | — | 77.8 | — | |
| Claude 3.5 Sonnet | 63 | — | — | 88.7 | — | 59.4 | — | — | 92 | |
| Mistral Medium 3.5 | 63 | $1.5 | $7.5 | — | — | — | — | 77.6 | — | |
| MiniMax M2.1 | 62 | $0.3 | $1.2 | — | 88 | 83 | 83 | 74 | — | |
| Llama 3.1 405B | 61 | self-host | self-host | 85.2 | — | — | — | — | — | |
| Nemotron 3 Ultra 550B A55B | 61 | self-host | self-host | — | 86.8 | — | — | 70.7 | — | |
| Claude Sonnet 4.5 | 60 | $3 | $15 | — | — | — | — | 77.2 | — | |
| GLM-4.5 | 58 | $0.6 | $2.2 | 90 | 84.6 | 79.1 | — | 64.2 | — | |
| Gemma 4 26B A4B Instruct | 58 | self-host | self-host | — | 82.6 | 82.3 | — | — | — | |
| DeepSeek V3.2-Exp | 55 | self-host | self-host | — | 85 | 79.9 | 89.3 | 67.8 | — | |
| Nemotron 3 Super 120B A12B | 49 | self-host | self-host | — | 83.73 | — | 90.21 | 60.47 | — | |
| Nemotron 3 Nano 30B A3B | 49 | self-host | self-host | — | 78.3 | — | 89.1 | — | — | |
| Llama 3.1 405B Instruct | 48 | self-host | self-host | 88.6 | — | 51.1 | — | — | — | |
| DeepSeek R1-0528 | 47 | self-host | self-host | — | 85 | 81 | 87.5 | 57.6 | — | |
| Gemini 2.5 Pro | 45 | $1.25 | $10 | — | — | 86.4 | 88 | 59.6 | — | |
| DeepSeek V3.1 | 45 | self-host | self-host | — | — | 80.1 | 88.4 | 66 | — | |
| Ministral 3 14B Reasoning | 44 | $0.2 | $0.2 | — | — | — | 85 | — | — | |
| GPT-4.1 | 44 | $2 | $8 | 90.2 | — | 66.3 | — | 54.6 | — | |
| GLM-4.7-Flash | 42 | self-host | self-host | — | — | — | 91.6 | 59.2 | — | |
| Grok 3 | 41 | — | — | — | 79.9 | 75.4 | — | — | — | |
| MiniMax M2 | 40 | $0.3 | $1.2 | — | 82 | 78 | 78 | 69.4 | — | |
| Olmo 3-Think 32B | 39 | self-host | self-host | 85.4 | — | — | 72.5 | — | — | |
| Gemma 4 12B Instruct | 39 | self-host | self-host | — | 77.2 | 78.8 | — | — | — | |
| Claude Haiku 4.5 | 38 | $1 | $5 | — | — | 73 | 80.7 | 73.3 | — | |
| Devstral 2 | 38 | $0.4 | $2 | — | — | — | — | 72.2 | — | |
| Kimi K2 | 37 | self-host | self-host | 87.8 | 81.1 | 75.1 | 49.5 | 65.8 | — | |
| Llama 4 Maverick Instruct | 37 | self-host | self-host | — | 80.5 | 69.8 | — | — | — | |
| Claude Opus 4 | 36 | $15 | $75 | — | — | 79.6 | 75.5 | 72.5 | — | |
| Qwen3 235B A22B | 35 | $0.7 | $2.8 | — | — | 71.1 | 81.5 | — | — | |
| DeepSeek R1 | 35 | self-host | self-host | — | — | 71.5 | — | — | — | |
| Qwen2.5-Coder 32B Instruct | 35 | self-host | self-host | 79.1 | 62.3 | 41.8 | — | — | 92.7 | |
| Gemini 1.5 Pro | 31 | — | — | 81.9 | — | — | — | — | 71.9 | |
| Devstral Small 2 | 31 | $0.1 | $0.3 | — | — | — | — | 68 | — | |
| DeepSeek V3 | 31 | self-host | self-host | 88.5 | 75.9 | 59.1 | — | 42 | — | |
| Granite 4.1 30B | 31 | self-host | self-host | 80.16 | 64.09 | 45.76 | — | — | 88.41 | |
| Llama 3.3 70B Instruct | 31 | self-host | self-host | — | 68.9 | 50.5 | — | — | 88.4 | |
| Claude Sonnet 4 | 30 | $3 | $15 | — | — | 75.4 | 70.5 | 72.7 | — | |
| MiniMax M1 | 30 | self-host | self-host | — | 81.1 | 70 | 76.9 | 56 | — | |
| Gemini 2.5 Flash | 27 | $0.3 | $2.5 | — | — | 80.8 | 75.6 | 54 | — | |
| Gemini 2.0 Flash | 27 | — | — | — | 77.6 | 60.1 | — | — | — | |
| Llama 3.1 70B Instruct | 26 | self-host | self-host | 83.6 | 66.4 | 48 | — | — | 80.5 | |
| Qwen2.5 72B Instruct | 25 | self-host | self-host | — | 71.1 | 49 | — | — | 86.6 | |
| Mistral Large 3 | 24 | $0.5 | $1.5 | — | — | 67.17 | — | — | — | |
| Gemma 3 27B Instruct | 23 | self-host | self-host | 76.9 | 67.5 | 42.4 | — | — | 87.8 | |
| Claude 3.7 Sonnet | 23 | — | — | — | — | 68 | — | 63.7 | — | |
| o1 | 22 | $15 | $60 | — | — | 78.3 | — | 40.9 | — | |
| Qwen3 32B | 21 | $0.16 | $0.64 | — | — | 68.4 | 72.9 | — | — | |
| DeepSeek R1-Distill-Qwen-32B | 21 | self-host | self-host | — | — | 62.1 | — | — | — | |
| Llama 4 Scout Instruct | 19 | self-host | self-host | — | 74.3 | 57.2 | — | — | — | |
| Magistral Medium | 18 | $2 | $5 | — | — | 70.8 | 64.9 | — | — | |
| Mixtral 8x22B | 14 | $2 | $6 | 77.75 | — | — | — | — | 45.1 | |
| Gemma 2 27B | 13 | self-host | self-host | 75.2 | — | — | — | — | 51.8 | |
| Llama 3.1 8B Instruct | 10 | self-host | self-host | 69.4 | 48.3 | 31.8 | — | — | 72.6 | |
| DeepSeek R1 Distill Llama 8B | 8 | self-host | self-host | — | — | 49 | — | — | — | |
| Llama 3.1 8B | 6 | self-host | self-host | 66.7 | — | — | — | — | — | |
| Devstral Small 1.1 | 4 | self-host | self-host | — | — | — | — | 53.6 | — | |
| Llama 3.2 3B Instruct | 0 | self-host | self-host | 63.4 | — | — | — | — | — | |
| DeepSeek V3.2 | — | self-host | self-host | — | — | — | — | — | — | |
| DeepSeek V3.2-Speciale | — | self-host | self-host | — | — | — | — | — | — | |
| Gemini 3.5 Flash | — | $1.5 | $9 | — | — | — | — | — | — | |
| Gemini 3.5 Flash-Lite | — | $0.3 | $2.5 | — | — | — | — | — | — | |
| Gemini 3.6 Flash | — | $1.5 | $7.5 | — | — | — | — | — | — | |
| Gemini 3 Deep Think | — | — | — | — | — | — | — | — | — | |
| GLM-4.6 | — | $0.6 | $2.2 | — | — | — | — | — | — | |
| GPT-4o | — | $2.5 | $10 | — | — | — | — | — | — | |
| GPT-5.2-Codex | — | $1.75 | $14 | — | — | — | — | — | — | |
| GPT-5.3-Codex | — | $1.75 | $14 | — | — | — | — | — | — | |
| Grok 4 | — | — | — | — | — | — | — | — | — | |
| Grok 4.1 | — | — | — | — | — | — | — | — | — | |
| Grok 4.1 Fast | — | — | — | — | — | — | — | — | — | |
| Grok 4.5 | — | $2 | $6 | — | — | — | — | — | — | |
| Hermes 3 Llama 3.1 8B | — | self-host | self-host | — | — | — | — | — | — | |
| Kimi K2.7-Code | — | $0.95 | $4 | — | — | — | — | — | — | |
| o3 | — | $2 | $8 | — | — | — | — | — | — | |
| o4-mini | — | $1.1 | $4.4 | — | — | — | — | — | — |