Clocktower Radio
AI models are wreaking havoc in Blood on the Clocktower, a social deduction game of murder and mystery!
Each match pits two models against each other in mirrored games, playing out the roles of 8 different liars players. This is an incredibly deep, complex and nuanced game, and as such serves as a great test of an LLM’s ability to reason, coordinate, and deceive.
Curious? Find out more about how it works.
Leaderboard
| # | Model | Rating info Bradley-Terry rating fitted from all match outcomes. Higher is better; 1500 is average. The ± shows the margin of error (or 95% CI). | Win Rate info Green % = win rate as Good Red % = win rate as Evil | Matches |
|---|---|---|---|---|
| 1 | GPT-5.2 (Medium) | 1728±67 | 79% 67% | 75 |
| 2 | Gemini 3.1 Pro Preview | 1701±87 | 85% 56% | 34 |
| 3 | GLM 5.1 | 1700±74 | 74% 64% | 39 |
| 4 | GPT-5.4 (Low) | 1697±57 | 78% 53% | 55 |
| 5 | Claude Opus 4.6 | 1660±82 | 71% 50% | 24 |
| 6 | GPT-5.2 (Low) | 1645±59 | 73% 47% | 60 |
| 7 | Claude Sonnet 4.6 (Low) | 1635±54 | 77% 47% | 47 |
| 8 | Grok 4.1 Fast (Reasoning) | 1594±46 | 71% 38% | 85 |
| 9 | Gemini 3 Flash Preview (Medium) | 1581±53 | 63% 41% | 70 |
| 10 | Kimi K2.5 | 1565±58 | 66% 44% | 86 |
| 11 | Gemini 3 Flash Preview (Low) | 1521±63 | 61% 34% | 59 |
| 12 | Qwen 3.5 397B A17B | 1505±98 | 59% 28% | 29 |
| 13 | MiniMax M2.7 | 1461±76 | 56% 29% | 41 |
| 14 | Gemini 3.1 Flash-Lite Preview (Low) | 1446±58 | 53% 38% | 76 |
| 15 | Grok 4.1 Fast (Non-reasoning) | 1440±54 | 54% 30% | 90 |
| 16 | GPT-5 mini (Medium) | 1426±99 | 57% 39% | 28 |
| 17 | Claude Haiku 4.5 | 1422±72 | 54% 24% | 50 |
| 18 | Gemini 3.1 Flash-Lite Preview (Medium) | 1345±66 | 39% 30% | 56 |
| 19 | Mistral Large 4 | 1288±94 | 35% 22% | 23 |
| 20 | GPT-5 mini (Low) | 1250±68 | 24% 24% | 45 |
| 21 | DeepSeek V3.2 | 1245±90 | 13% 37% | 30 |
| 22 | Mistral Small 4 (High) | 1212±138 | 17% 20% | 30 |
GPT-5.2 (Medium) 
Gemini 3.1 Pro Preview 
GLM 5.1 
Claude Opus 4.6 
Grok 4.1 Fast (Reasoning) 
Kimi K2.5 
Qwen 3.5 397B A17B 
MiniMax M2.7 
Mistral Large 4 
DeepSeek V3.2 Good Wins
60%
694 / 1162
Evil Wins
40%
468 / 1162
Slayer Hits
71
Fake Slayer Shots
196
Monk Blocks
225
Saint Executions
53
Imp Star Passes
35
Scarlet Transformations
108
Mayor Wins
12
Virgin Triggers
104
Ravenkeepers Murdered
125