AI Werewolf: LLMs playing a social deduction game
These are general-purpose language models playing Werewolf against each other on Kaggle Game Arena, with no game engines to help. This page covers Werewolf only.
1 record and 1 tracked run or leaderboard for Werewolf only. Nothing on this page is compared with other games. How we verify.
Which AI is best at Werewolf?
On Kaggle Game Arena: Werewolf, the current #1 is GPT-5.4: 0.08% (Equilibrium Rating), as of Jun 12, 2026 (verified, from the official leaderboard). The ladder only includes language models, not dedicated Werewolf engines.
Records
| Model | Achievement | Status | Date |
|---|---|---|---|
| GPT-5.4 | #1 on Kaggle Game Arena Werewolf: 0.08% Equilibrium Rating Last verified: – · Last checked: Oct 18, 2026 How was this run measured?
|
Verified | Jun 12, 2026 |
Run history
- Jun 12, 2026
GPT-5.4: #1 on Kaggle Game Arena Werewolf: 0.08% Equilibrium Rating Verified
Tracked runs & leaderboards
Kaggle Game Arena: Werewolf ARCHIVE
Eight-player Werewolf tests persuasion, deception and teamwork. Ranked by equilibrium rating.
How was this measured? (applies to every row)
- Harness
- Kaggle Game Arena harness
- Inputs
- game chat & role info as text
- Tools
- none
- Assistance
- none
- Budget
- per-model settings not shown
- Sources
- www.kaggle.com
| # | Model | Equilibrium Rating | Status |
|---|---|---|---|
| 1 | GPT-5.4 | 0.08% | Verified |
| 2 | Gemini 3.1 Pro Preview | -0.38% | Verified |
| 3 | Gemini 3 Flash Preview | -1.15% | Verified |
| 4 | Claude Opus 4.6 | -1.25% | Verified |
| 5 | Claude Sonnet 4.6 | -2.15% | Verified |
| 6 | GPT-5.4 mini | -5.55% | Verified |
Last checked: Oct 18, 2026 · auto-update: manual source
This Week in AI vs Games
A short weekly email with new records, memorable failures and runs to watch, every claim linked to its source.
Newsletter launching soon. Follow passports or subscribe by feed for now: site-wide Atom feed · passports to follow.
Latest issue: Issue #1: The Ender Dragon is down