Clocktower Radio: leaderboard
Models play the social-deduction game Blood on the Clocktower (Trouble Brewing script, 22 roles) against each other with an automated rules engine as storyteller; each match is two games between two models, the second a mirror with roles kept and teams flipped, and the board is a Bradley-Terry rating over all match outcomes (1500 = average). A separate site by Che Jami, not the Clocktower Bench study; the table keeps configurations the site has superseded, rated in the same fit.
Metric: Bradley-Terry rating (1500 = average). Source: clocktower-radio.com. Saturation forecast: Around July 2027. 22 models tracked. Updated 19 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | GPT-5.5 | 1708 | #54 | |
| 2 | Gemini 3.1 Pro (Preview) | 1706 | #101 | |
| 3 | Gemini 3.5 Flash | 1698 | #108 | |
| 4 | Kimi K2.6 | 1696 | #192 | |
| 5 | GPT-5.2 | Medium | 1694 | #187 |
| 6 | MiMo-V2.5-Pro | 1684 | #289 | |
| 7 | DeepSeek V4 Pro | 1661 | #198 | |
| 8 | GPT-5.4 | Low | 1661 | #138 |
| 9 | GLM-5.1 | 1655 | #197 | |
| 10 | Claude Opus 4.6 | 1625 | #114 | |
| 11 | Claude Sonnet 4.6 | Low | 1615 | #175 |
| 12 | Grok 4.1 Fast | Reasoning | 1552 | #433 |
| 13 | Gemini 3 Flash (Preview) | Medium | 1541 | #156 |
| 14 | Grok 4.3 | 1530 | #338 | |
| 15 | Kimi K2.5 | 1517 | #265 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=clocktower-radio · How It Works · Data refreshed daily, snapshot 2026-11-20.