评测来源/MysteryMechanism
参与排名推理
MysteryMechanism
Vals AI · MysteryMechanism 的公开模型评测结果。
本来源的模型成绩
| GPT-6 Astra | 53.15 | 76.2 | 2026-11-05 |
| Claude Opus 5.5 | 49.55 | 71.6 | 2026-11-05 |
| Claude Sonnet 5.5 | 49.1 | 71.0 | 2026-11-05 |
| Claude Fable 5.1 | 47.75 | 69.3 | 2026-11-05 |
| GPT-6.1 Sol | 46.4 | 67.6 | 2026-11-05 |
| Gemini 4 Argon | 45.49 | 66.5 | 2026-11-05 |
| Claude Opus 5 | 37.39 | 56.3 | 2026-11-05 |
| Gemini 3.8 Flash | 36.49 | 55.1 | 2026-11-05 |
| Muse Spark 1.3 | 36.04 | 54.6 | 2026-11-05 |
| Claude Haiku 5.5 | 35.13 | 53.4 | 2026-11-05 |
| GPT-5.6 Sol | 33.33 | 51.2 | 2026-11-05 |
| Grok 4.6 | 30.63 | 47.8 | 2026-11-05 |
| GPT-6 Sol | 30.18 | 47.2 | 2026-11-05 |
| Grok 4.7 | 25.23 | 40.9 | 2026-11-05 |
| Qwen3.8 Max | 23.87 | 39.2 | 2026-11-05 |
| GLM 5.3 | 22.97 | 38.1 | 2026-11-05 |
| MiMo V2.6 Flash | 21.62 | 36.4 | 2026-11-05 |
| MiMo V2.6 Flash | 21.62 | 36.4 | 2026-10-17 |
| MiMo V2.6 Flash | 21.62 | 36.4 | 2026-10-18 |
| DeepSeek V4.1 Flash | 21.17 | 35.8 | 2026-11-05 |
| GPT-6 Luna | 19.37 | 33.6 | 2026-11-05 |
| Step 5 Preview | 18.47 | 32.4 | 2026-11-05 |
| MiMo V2.6 Pro | 15.31 | 28.4 | 2026-11-05 |
| GPT-5.6 Luna | 14.41 | 27.3 | 2026-11-05 |
| Mistral Large 4 | 12.16 | 24.5 | 2026-10-31 |