CoupBench
83 games of Coup between four LLMs, with every hidden card shown. Run the benchmark / contribute
| Game | Winner | Turns |
|---|---|---|
| Game 1 | Claude Opus 5.5 | 9 |
| Game 2 | MiMo V2.6 Pro | 9 |
| Game 3 | Claude Opus 5.5 | 9 |
| Game 4 | MiMo V2.6 Pro | 13 |
| Game 5 | GPT-6.1 Sol | 10 |
| Game 6 | GPT-6.1 Sol | 12 |
| Game 7 | MiMo V2.6 Pro | 10 |
| Game 8 | GPT-6.1 Sol | 11 |
| Game 9 | GPT-6.1 Sol | 14 |
| Game 10 | GPT-6.1 Sol | 18 |
| Game 11 | MiMo V2.6 Pro | 9 |
| Game 12 | MiMo V2.6 Pro | 13 |
| Game 13 | Claude Opus 5.5 | 9 |
| Game 14 | GPT-6.1 Sol | 14 |
| Game 15 | GPT-6.1 Sol | 15 |
| Game 16 | Claude Opus 5.5 | 8 |
| Game 17 | Mistral Large 4 | 8 |
| Game 18 | MiMo V2.6 Pro | 9 |
| Game 19 | GPT-6.1 Sol | 14 |
| Game 20 | GPT-6.1 Sol | 11 |
| Game 21 | MiMo V2.6 Pro | 13 |
| Game 22 | MiMo V2.6 Pro | 9 |
| Game 23 | Claude Opus 5.5 | 13 |
| Game 24 | Claude Opus 5.5 | 10 |
| Game 25 | Claude Opus 5.5 | 8 |
| Game 26 | Claude Opus 5.5 | 17 |
| Game 27 | Claude Opus 5.5 | 11 |
| Game 28 | Mistral Large 4 | 21 |
| Game 29 | Claude Opus 5.5 | 14 |
| Game 30 | MiMo V2.6 Pro | 12 |
| Game 31 | Claude Opus 5.5 | 11 |
| Game 32 | MiMo V2.6 Pro | 12 |
| Game 33 | Claude Opus 5.5 | 12 |
| Game 34 | GPT-6.1 Sol | 7 |
| Game 35 | Claude Opus 5.5 | 9 |
| Game 36 | Claude Opus 5.5 | 9 |
| Game 37 | MiMo V2.6 Pro | 12 |
| Game 38 | MiMo V2.6 Pro | 15 |
| Game 39 | Mistral Large 4 | 12 |
| Game 40 | Claude Opus 5.5 | 10 |
| Game 41 | MiMo V2.6 Pro | 11 |
| Game 42 | MiMo V2.6 Pro | 10 |
| Game 43 | MiMo V2.6 Pro | 13 |
| Game 44 | Mistral Large 4 | 15 |
| Game 45 | Mistral Large 4 | 11 |
| Game 46 | GPT-6.1 Sol | 9 |
| Game 47 | GPT-6.1 Sol | 19 |
| Game 48 | Mistral Large 4 | 10 |
| Game 49 | Claude Opus 5.5 | 11 |
| Game 50 | MiMo V2.6 Pro | 16 |
| Game 51 | Claude Opus 5.5 | 18 |
| Game 52 | GPT-6.1 Sol | 22 |
| Game 53 | MiMo V2.6 Pro | 10 |
| Game 54 | MiMo V2.6 Pro | 13 |
| Game 55 | Mistral Large 4 | 9 |
| Game 56 | Mistral Large 4 | 10 |
| Game 57 | Claude Opus 5.5 | 18 |
| Game 58 | GPT-6.1 Sol | 12 |
| Game 59 | Claude Opus 5.5 | 13 |
| Game 60 | GPT-6.1 Sol | 10 |
| Game 61 | GPT-6.1 Sol | 12 |
| Game 62 | GPT-6.1 Sol | 11 |
| Game 63 | GPT-6.1 Sol | 13 |
| Game 64 | GPT-6.1 Sol | 11 |
| Game 65 | GPT-6.1 Sol | 21 |
| Game 66 | MiMo V2.6 Pro | 10 |
| Game 67 | MiMo V2.6 Pro | 9 |
| Game 68 | Mistral Large 4 | 9 |
| Game 69 | MiMo V2.6 Pro | 5 |
| Game 70 | Claude Opus 5.5 | 10 |
| Game 71 | Claude Opus 5.5 | 8 |
| Game 72 | MiMo V2.6 Pro | 13 |
| Game 73 | Claude Opus 5.5 | 15 |
| Game 74 | MiMo V2.6 Pro | 13 |
| Game 75 | GPT-6.1 Sol | 13 |
| Game 76 | GPT-6.1 Sol | 15 |
| Game 77 | MiMo V2.6 Pro | 14 |
| Game 78 | Claude Opus 5.5 | 13 |
| Game 79 | GPT-6.1 Sol | 26 |
| Game 80 | Mistral Large 4 | 13 |
| Game 81 | GPT-6.1 Sol | 17 |
| Game 82 | MiMo V2.6 Pro | 16 |
| Game 83 | Claude Opus 5.5 | 11 |