评测来源/Terminal-Bench 4.0(AA 复跑)
参与排名编程
Terminal-Bench 4.0(AA 复跑)
Artificial Analysis · Terminal-Bench 4.0(AA 复跑) 的公开模型评测结果。
本来源的模型成绩
| Claude Sonnet 5.5 | 0.63636364 | 89.1 | 2026-11-05 |
| GPT-6 Astra | 0.5959596 | 86.0 | 2026-11-05 |
| Claude Opus 5.5 | 0.5959596 | 86.0 | 2026-11-05 |
| Gemini 4 Argon | 0.57070707 | 84.0 | 2026-11-05 |
| Muse Wonder Full | 0.57070707 | 84.0 | 2026-10-17 |
| Muse Wonder Full | 0.57070707 | 84.0 | 2026-10-18 |
| Muse Wonder Full | 0.57070707 | 84.0 | 2026-11-05 |
| GPT-6.1 Sol | 0.56060606 | 83.2 | 2026-11-05 |
| GPT-6.1 Terra | 0.55555556 | 82.8 | 2026-11-05 |
| Claude Fable 5.1 | 0.55050505 | 82.4 | 2026-11-05 |
| Muse Wonder | 0.52020202 | 80.0 | 2026-10-17 |
| Muse Wonder | 0.52020202 | 80.0 | 2026-11-05 |
| Muse Wonder | 0.52020202 | 80.0 | 2026-10-18 |
| Claude Opus 5 | 0.48989899 | 77.6 | 2026-11-05 |
| GPT-6 Sol | 0.43939394 | 73.6 | 2026-11-05 |
| Claude Fable 5 | 0.42424242 | 72.4 | 2026-11-05 |
| GLM 5.3 | 0.41919192 | 72.0 | 2026-11-05 |
| GPT-5.6 Sol | 0.3989899 | 70.4 | 2026-11-05 |
| GPT-5.6 Terra | 0.35353535 | 66.8 | 2026-11-05 |
| MiMo V2.6 Pro | 0.34848485 | 66.4 | 2026-11-05 |
| DeepSeek V4.1 Flash 1017 | 0.33838384 | 65.6 | 2026-11-05 |
| Ling-3.1-flash | 0.33333333 | 65.2 | 2026-10-18 |
| Ling-3.1-flash | 0.33333333 | 65.2 | 2026-11-05 |
| Ling-3.1-flash | 0.33333333 | 65.2 | 2026-10-17 |
| Muse Spark 1.3 | 0.33333333 | 65.2 | 2026-11-05 |
| Step 5 Preview | 0.33333333 | 65.2 | 2026-11-05 |
| Ling-3.1-flash-1019 | 0.32828283 | 64.8 | 2026-11-05 |
| GLM-5.3 Flash | 0.32828283 | 64.8 | 2026-10-17 |
| GLM-5.3 Flash | 0.32828283 | 64.8 | 2026-11-05 |
| GLM-5.3 Flash | 0.32828283 | 64.8 | 2026-10-18 |
| Claude Haiku 5.5 | 0.32828283 | 64.8 | 2026-11-05 |
| DeepSeek V4.1 Flash | 0.26767677 | 60.0 | 2026-11-05 |
| Mistral Large 4 | 0.26767677 | 60.0 | 2026-10-28 |
| Grok 4.7 | 0.25757576 | 59.2 | 2026-11-05 |
| MiniMax M3.1 Flash | 0.25757576 | 59.2 | 2026-11-05 |
| Mistral Large 4 | 0.24747475 | 58.4 | 2026-11-05 |
| MiMo V2.6 Flash | 0.22727273 | 56.8 | 2026-10-17 |
| MiMo V2.6 Flash | 0.22727273 | 56.8 | 2026-11-05 |
| MiMo V2.6 Flash | 0.22727273 | 56.8 | 2026-10-18 |
| Claude Opus 4.8 | 0.21717172 | 56.1 | 2026-11-05 |
| Grok 4.6 | 0.21212121 | 55.7 | 2026-11-05 |
| Gemini 3.8 Flash | 0.1969697 | 54.5 | 2026-11-05 |
| Qwen3.8 Max | 0.18686869 | 53.7 | 2026-11-05 |
| GPT-5.5 | 0.14646465 | 50.5 | 2026-11-05 |
| DeepSeek V4 Pro | 0.14646465 | 50.5 | 2026-11-05 |
| Claude Sonnet 5 | 0.14141414 | 50.1 | 2026-11-05 |
| DeepSeek V4 Pro 0813 | 0.14141414 | 50.1 | 2026-11-05 |
| Kimi K3 | 0.12626263 | 48.9 | 2026-11-05 |
| Kimi K3 | 0.12626263 | 48.9 | 2026-10-27 |
| GPT-6 Luna | 0.12626263 | 48.9 | 2026-11-05 |
| DeepSeek V4 Flash 0731 | 0.12121212 | 48.5 | 2026-11-05 |
| GPT-5.6 Luna | 0.11616162 | 48.1 | 2026-11-05 |
| Grok 4.5 | 0.10606061 | 47.3 | 2026-11-05 |
| Gemini 3.6 Flash | 0.07070707 | 44.5 | 2026-11-05 |
| Muse Spark 1.2 | 0.07070707 | 44.5 | 2026-11-05 |
| Muse Spark 1.1 | 0.06060606 | 43.7 | 2026-11-05 |
| Gemini 3.1 Pro Preview | 0.04040404 | 42.1 | 2026-11-05 |
| Claude Sonnet 4.6 | 0.03030303 | 41.3 | 2026-11-05 |
| GPT-5.4 mini | 0.02020202 | 40.5 | 2026-11-05 |
| GLM-5.1 | 0.02020202 | 40.5 | 2026-11-05 |
| MiniMax-M3 | 0.02020202 | 40.5 | 2026-11-05 |
| Qwen3.7 Max | 0.01515152 | 40.1 | 2026-11-05 |
| Qwen3.7 Plus | 0.01010101 | 39.7 | 2026-11-05 |
| Kimi K2.7 Code | 0.01010101 | 39.7 | 2026-11-05 |
| GLM-5.2 | 0.01010101 | 39.7 | 2026-11-05 |
| Inkling | 0.01010101 | 39.7 | 2026-11-05 |
| Gemini 3.5 Flash Lite | 0.01010101 | 39.7 | 2026-11-05 |
| Inkling Small | 0.01010101 | 39.7 | 2026-11-05 |
| Qwen3.5 9B | 0.00505051 | 39.3 | 2026-11-05 |
| Trinity Large Thinking | 0.00505051 | 39.3 | 2026-11-05 |
| Kimi K2.6 | 0.00505051 | 39.3 | 2026-11-05 |
| Gemini 3.1 Flash Lite | 0.00505051 | 39.3 | 2026-11-05 |
| Ring-2.6-1T | 0.00505051 | 39.3 | 2026-11-05 |
| Command A Plus | 0.00505051 | 39.3 | 2026-11-05 |
| Nemotron 3 Ultra 550B A55B | 0.00505051 | 39.3 | 2026-11-05 |
| North Mini Code | 0.00505051 | 39.3 | 2026-11-05 |
| Hy3 | 0.00505051 | 39.3 | 2026-11-05 |
| o3-mini | 0 | 38.9 | 2026-10-11 |
| DeepSeek-R1 | 0 | 38.9 | 2026-11-05 |
| o3 Mini High | 0 | 38.9 | 2026-11-05 |
| DeepSeek V3 0324 | 0 | 38.9 | 2026-11-05 |
| Qwen3 32B | 0 | 38.9 | 2026-11-05 |
| Llama 4 Maverick | 0 | 38.9 | 2026-11-05 |
| Llama 4 Scout | 0 | 38.9 | 2026-11-05 |
| Qwen3 8B | 0 | 38.9 | 2026-11-05 |
| Qwen3 14B | 0 | 38.9 | 2026-11-05 |
| Gemini 2.5 Pro | 0 | 38.9 | 2026-11-05 |
| gpt-oss-120b | 0 | 38.9 | 2026-11-05 |
| gpt-oss-20b | 0 | 38.9 | 2026-11-05 |
| GPT-5 mini | 0 | 38.9 | 2026-11-05 |
| DeepSeek V3.1 Terminus | 0 | 38.9 | 2026-11-05 |
| Claude Sonnet 4.5 | 0 | 38.9 | 2026-11-05 |
| Claude Haiku 4.5 | 0 | 38.9 | 2026-11-05 |
| Mistral Large 3 | 0 | 38.9 | 2026-11-05 |
| Ministral 3 14B | 0 | 38.9 | 2026-11-05 |
| Ministral 3 8B | 0 | 38.9 | 2026-11-05 |
| Ministral 3 3B | 0 | 38.9 | 2026-11-05 |
| Nemotron 3 Nano 30B A3B | 0 | 38.9 | 2026-11-05 |
| Solar Pro 3 | 0 | 38.9 | 2026-11-05 |
| Qwen3 Coder Next | 0 | 38.9 | 2026-11-05 |
| Qwen3.5 397B-A17B | 0 | 38.9 | 2026-11-05 |
| Qwen3.5 122B-A10B | 0 | 38.9 | 2026-11-05 |
| Mercury 2 | 0 | 38.9 | 2026-11-05 |
| Nemotron 3 Super 120B A12B | 0 | 38.9 | 2026-11-05 |
| MiniMax-M2.7 | 0 | 38.9 | 2026-11-05 |
| Qwen3.6 35B-A3B | 0 | 38.9 | 2026-11-05 |
| Grok 4.3 | 0 | 38.9 | 2026-11-05 |
| Grok 4.3 | 0 | 38.9 | 2026-10-27 |
| Qwen3.6 27B | 0 | 38.9 | 2026-11-05 |
| MiMo-V2.5 | 0 | 38.9 | 2026-11-05 |
| MiMo-V2.5-Pro | 0 | 38.9 | 2026-11-05 |
| Mistral Medium 3.5 | 0 | 38.9 | 2026-11-05 |
| LongCat-2.0 | 0 | 38.9 | 2026-11-05 |
| Ling-3.0-flash (free) | 0 | 38.9 | 2026-11-05 |