评测来源/IFBench(Artificial Analysis)
观察中知识与语言
IFBench(Artificial Analysis)
Artificial Analysis · IFBench(Artificial Analysis) 的公开模型评测结果。
本来源的模型成绩
| Grok 4.3 | 0.83333333 | 83.3 | 2026-11-05 |
| Grok 4.20 (Reasoning) | 0.8292517 | 82.9 | 2026-11-05 |
| MiniMax-M3 | 0.82857143 | 82.9 | 2026-11-05 |
| Nemotron 3 Ultra 550B A55B | 0.81360544 | 81.4 | 2026-11-05 |
| Grok 4.20 | 0.8122449 | 81.2 | 2026-10-11 |
| Qwen3.7 Max | 0.80544218 | 80.5 | 2026-11-05 |
| Nemotron Cascade 2 30B A3B | 0.80408163 | 80.4 | 2026-11-05 |
| MiMo-V2.5-Pro | 0.79863946 | 79.9 | 2026-11-05 |
| Qwen3.5 397B-A17B | 0.7877551 | 78.8 | 2026-11-05 |
| Gemini 3 Flash Preview | 0.77959184 | 78.0 | 2026-11-05 |
| Qwen3.7 Plus | 0.77959184 | 78.0 | 2026-11-05 |
| Gemini 3.1 Flash Lite | 0.77210884 | 77.2 | 2026-11-05 |
| Gemini 3.1 Pro Preview | 0.77142857 | 77.1 | 2026-11-05 |
| Qwen3.6 Max Preview | 0.76598639 | 76.6 | 2026-11-05 |
| DeepSeek V4 Pro | 0.76462585 | 76.5 | 2026-11-05 |
| GLM-5.1 | 0.76258503 | 76.3 | 2026-11-05 |
| Kimi K2.6 | 0.75986395 | 76.0 | 2026-11-05 |
| GPT-5.5 | 0.7585034 | 75.9 | 2026-11-05 |
| Qwen3.5 122B-A10B | 0.75714286 | 75.7 | 2026-11-05 |
| MiniMax-M2.7 | 0.75714286 | 75.7 | 2026-11-05 |
| Qwen3.5 27B | 0.75578231 | 75.6 | 2026-11-05 |
| GPT-5 mini | 0.75442177 | 75.4 | 2026-11-05 |
| GPT-5.2 | 0.75442177 | 75.4 | 2026-11-05 |
| Qwen3.6 Plus | 0.75170068 | 75.2 | 2026-11-05 |
| GPT-5.4 | 0.73945578 | 73.9 | 2026-11-05 |
| Command A Plus | 0.73945578 | 73.9 | 2026-11-05 |
| Gemma 4 12B Base | 0.73537415 | 73.5 | 2026-11-05 |
| GLM-5.2 | 0.73333333 | 73.3 | 2026-11-05 |
| GPT-5.4 mini | 0.73265306 | 73.3 | 2026-11-05 |
| GLM-5-Turbo | 0.73197279 | 73.2 | 2026-11-05 |
| GPT-5 | 0.73061224 | 73.1 | 2026-11-05 |
| GPT-5.6 Sol | 0.72653061 | 72.7 | 2026-11-05 |
| Qwen3.5 35B-A3B | 0.72517007 | 72.5 | 2026-11-05 |
| MiniMax-M2 | 0.72312925 | 72.3 | 2026-11-05 |
| GLM-5 | 0.72312925 | 72.3 | 2026-11-05 |
| MiniMax-M2.5 | 0.71632653 | 71.6 | 2026-11-05 |
| Nemotron 3 Super 120B A12B | 0.71496599 | 71.5 | 2026-11-05 |
| o3 | 0.71428571 | 71.4 | 2026-11-05 |
| GPT-5.6 Terra | 0.7122449 | 71.2 | 2026-11-05 |
| Solar Pro 3 | 0.71201814 | 71.2 | 2026-11-05 |
| Nemotron 3 Nano 30B A3B | 0.71088435 | 71.1 | 2026-11-05 |
| Qwen3 Max Thinking | 0.70748299 | 70.7 | 2026-11-05 |
| Gemini 3 Pro Preview | 0.70408163 | 70.4 | 2026-11-05 |
| o1 | 0.70340136 | 70.3 | 2026-11-03 |
| Kimi K2.5 | 0.70204082 | 70.2 | 2026-11-05 |
| MiniMax-M2.1 | 0.69863946 | 69.9 | 2026-11-05 |
| Mercury 2 | 0.69795918 | 69.8 | 2026-11-05 |
| gpt-oss-120b | 0.68979592 | 69.0 | 2026-11-05 |
| MiMo-V2-Pro | 0.68843537 | 68.8 | 2026-11-05 |
| Mistral Medium 3.5 | 0.6877551 | 68.8 | 2026-11-05 |
| o4-mini | 0.68707483 | 68.7 | 2026-10-11 |
| o4 Mini High | 0.68707483 | 68.7 | 2026-11-05 |
| GLM-4.7 | 0.67891156 | 67.9 | 2026-11-05 |
| GPT-5 nano | 0.6755102 | 67.6 | 2026-11-05 |
| Qwen3.6 27B | 0.6755102 | 67.6 | 2026-11-05 |
| Step 3.7 Flash | 0.67278912 | 67.3 | 2026-11-05 |
| o3-mini | 0.67142857 | 67.1 | 2026-10-11 |
| o3 Mini High | 0.67142857 | 67.1 | 2026-11-05 |
| MiMo-V2.5 | 0.67142857 | 67.1 | 2026-11-05 |
| Qwen3.5 9B | 0.66734694 | 66.7 | 2026-11-05 |
| KAT-Coder-Pro V2 | 0.66666667 | 66.7 | 2026-11-05 |
| Step 3.5 Flash 2603 | 0.66530612 | 66.5 | 2026-11-05 |
| Nex-N2-Pro | 0.66190476 | 66.2 | 2026-11-05 |
| gpt-oss-20b | 0.65102041 | 65.1 | 2026-11-05 |
| Step 3.5 Flash | 0.64557823 | 64.6 | 2026-11-05 |
| Qwen3.6 35B-A3B | 0.64353741 | 64.4 | 2026-11-05 |
| MiMo-V2-Flash | 0.64217687 | 64.2 | 2026-11-05 |
| Claude Fable 5 | 0.63469388 | 63.5 | 2026-11-05 |
| Nemotron 3 Nano Omni 30B A3B Reasoning | 0.63197279 | 63.2 | 2026-11-05 |
| Hy3 preview | 0.63129252 | 63.1 | 2026-11-05 |
| Kimi K2.7 Code | 0.63129252 | 63.1 | 2026-11-05 |
| Claude Opus 4.8 | 0.62244898 | 62.2 | 2026-11-05 |
| GLM-5V-Turbo | 0.61088435 | 61.1 | 2026-11-05 |
| GLM-4.7-Flash | 0.60816327 | 60.8 | 2026-11-05 |
| DeepSeek V3.2 | 0.60680272 | 60.7 | 2026-11-05 |
| Claude Opus 4.7 | 0.58639456 | 58.6 | 2026-11-05 |
| Claude Opus 4.5 | 0.57959184 | 58.0 | 2026-11-05 |
| North Mini Code | 0.5755102 | 57.6 | 2026-11-05 |
| Ling-2.6-flash | 0.57414966 | 57.4 | 2026-11-05 |
| Claude Sonnet 4.5 | 0.57278912 | 57.3 | 2026-11-05 |
| DeepSeek V3.1 Terminus | 0.57006803 | 57.0 | 2026-11-05 |
| Ling-2.6-1T | 0.56870748 | 56.9 | 2026-11-05 |
| Claude Sonnet 4.6 | 0.56598639 | 56.6 | 2026-11-05 |
| Trinity Large Thinking | 0.56258503 | 56.3 | 2026-11-05 |
| Claude Haiku 4.5 | 0.54285714 | 54.3 | 2026-11-05 |
| DeepSeek V3.2 Exp | 0.5414966 | 54.1 | 2026-11-05 |
| MiMo-V2-Omni | 0.53537415 | 53.5 | 2026-11-05 |
| Claude Opus 4.6 | 0.53129252 | 53.1 | 2026-11-05 |
| Gemini 2.5 Flash | 0.50272109 | 50.3 | 2026-11-05 |
| Gemini 2.5 Flash-Lite | 0.49863946 | 49.9 | 2026-11-05 |
| Olmo 3 32B Think | 0.49115646 | 49.1 | 2026-11-05 |
| Gemini 2.5 Pro | 0.48707483 | 48.7 | 2026-11-05 |
| Grok 4.20 (Non-Reasoning) | 0.47823129 | 47.8 | 2026-11-05 |
| Qwen3 235B A22B Instruct 2507 | 0.46054422 | 46.1 | 2026-11-05 |
| Ring-2.6-1T | 0.44557823 | 44.6 | 2026-11-05 |
| Qwen3 Max | 0.4414966 | 44.1 | 2026-11-05 |
| GLM-4.5 | 0.44081633 | 44.1 | 2026-11-05 |
| GLM-4.6 | 0.43401361 | 43.4 | 2026-11-05 |
| Llama 4 Maverick | 0.42993197 | 43.0 | 2026-11-05 |
| Qwen3 VL 235B A22B Instruct | 0.42653061 | 42.7 | 2026-11-05 |
| Kimi K2 0905 | 0.4170068 | 41.7 | 2026-11-05 |
| Qwen3 30B A3B | 0.41496599 | 41.5 | 2026-11-05 |
| DeepSeek V3.1 | 0.41496599 | 41.5 | 2026-11-05 |
| DeepSeek V3 0324 | 0.41020408 | 41.0 | 2026-11-05 |
| Qwen3 14B | 0.40544218 | 40.5 | 2026-11-05 |
| Qwen3-Coder 480B-A35B Instruct | 0.4047619 | 40.5 | 2026-11-05 |
| Gemini 2.0 Flash | 0.40204082 | 40.2 | 2026-11-05 |
| Qwen3-Next 80B-A3B Instruct | 0.39659864 | 39.7 | 2026-11-05 |
| Llama 4 Scout | 0.3952381 | 39.5 | 2026-11-05 |
| Llama 3.3 Nemotron Super 49B v1 | 0.39455782 | 39.5 | 2026-11-05 |
| Mistral Medium 3.5 | 0.39251701 | 39.3 | 2026-11-05 |
| Qwen3 VL 32B Instruct | 0.39183673 | 39.2 | 2026-11-05 |
| DeepSeek-R1 | 0.38979592 | 39.0 | 2026-11-05 |
| Qwen3 235B-A22B | 0.38707483 | 38.7 | 2026-11-05 |
| Granite 4.1 8B | 0.38639456 | 38.6 | 2026-11-05 |
| GLM-4.5-Air | 0.3755102 | 37.6 | 2026-11-05 |
| Qwen2.5 72B Instruct | 0.36870748 | 36.9 | 2026-11-05 |
| Command A | 0.36462585 | 36.5 | 2026-11-05 |
| Qwen3 32B | 0.36326531 | 36.3 | 2026-11-05 |
| Mistral Large 3 | 0.36190476 | 36.2 | 2026-11-05 |
| Qwen3 Coder Next | 0.35238095 | 35.2 | 2026-11-05 |
| Sarvam 105B | 0.34353741 | 34.4 | 2026-11-05 |
| GLM-4.5V | 0.34217687 | 34.2 | 2026-11-05 |
| Qwen3 8B | 0.33469388 | 33.5 | 2026-11-05 |
| GPT-4 | 0.33197279 | 33.2 | 2026-11-05 |
| Qwen3 VL 30B A3B Instruct | 0.33129252 | 33.1 | 2026-11-05 |
| Qwen3 30B A3B Instruct 2507 | 0.33061224 | 33.1 | 2026-11-05 |
| Qwen3-Coder 30B-A3B Instruct | 0.32653061 | 32.7 | 2026-11-05 |
| Qwen3 VL 8B Instruct | 0.32312925 | 32.3 | 2026-11-05 |
| Ministral 3 14B | 0.32040816 | 32.0 | 2026-11-05 |
| Nemotron Nano 12B v2 VL | 0.31904762 | 31.9 | 2026-11-05 |
| Reka Flash 3 | 0.30408163 | 30.4 | 2026-11-05 |
| GLM-4.6V | 0.30068027 | 30.1 | 2026-11-05 |
| Ministral 3 8B | 0.29115646 | 29.1 | 2026-11-05 |
| Nemotron Nano 9B v2 | 0.27619048 | 27.6 | 2026-11-05 |
| R1 Distill Llama 70B | 0.2755102 | 27.6 | 2026-11-05 |
| Ministral 3 3B | 0.26802721 | 26.8 | 2026-11-05 |
| Sarvam 30B | 0.26462585 | 26.5 | 2026-11-05 |
| Mistral Small 3 | 0.26394558 | 26.4 | 2026-11-05 |
| Granite 4.0 Micro | 0.24761905 | 24.8 | 2026-11-05 |
| Phi 4 | 0.23537415 | 23.5 | 2026-11-05 |