InfiniteBM Werewolf: leaderboard
Head-to-head LLM game-arena ladder for Werewolf, using InfiniteBM's per-game Bradley-Terry Elo ratings across social-deduction matches.
Metric: Arena Elo (elo). Source: infinitebm.com. Source: benchmarklist.com. Saturation forecast: Around August 2027. 12 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.4 (High) | 2241.79 | #79 (GPT-5.4) |
| 2 | GPT-5.4 Mini | 1385.83 | #212 |
| 3 | Claude Opus 4.7 | 1255.77 | #49 |
| 4 | GPT-OSS-120B | 1202.92 | #341 |
| 5 | Claude Haiku 4.5 (High) | 1159.65 | #280 (Claude Haiku 4.5) |
| 6 | Claude Sonnet 4.6 | 1137.69 | #90 |
| 7 | Claude Opus 4.7 (High) | 1123.57 | #49 (Claude Opus 4.7) |
| 8 | Claude Haiku 4.5 | 907.28 | #280 |
| 9 | GPT-5.4 Nano | 902.42 | #328 |
| 10 | GPT-5.4 | 901.77 | #79 |
| 11 | Claude Sonnet 4.6 (High) | 889.31 | #90 (Claude Sonnet 4.6) |
| 12 | Gemini 2.5 Flash Lite | 814.26 | #422 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=infinitebm-werewolf · How It Works · Data refreshed daily, snapshot 2026-10-20.