Werewolf Arena
Models compete in Werewolf with strategic speaking, deception, deduction, and persuasion.
The July 2024 paper reports an arena tournament with Gemini and GPT models. The abstract does not state the best score.
- Made by
- Werewolf Arena authors
- Released
- July 2024
- Kind
- Multi-agent games
- Level
- Everyday
- Scored
- Settled by events
- Answers
- Agent task
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Multi-agent
- Environment
- Werewolf
- Items from
- Live play or votes
- Refresh
- Live
- Run by
- Anyone
- In views
- Games, Agents, Kept fresh
- Last model added
- December 2023
- Scores refreshed
- November 20th, 2026
GPT-4 (snapshot unspecified) tops the leaderboard with 75.0 Gemini 1.0 Pro leads with 26.7
Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. The paper reports no whole-game score, so this is the Unmasked Wolf percentage, the success-related Seer measure. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. The best model we track is Gemini 1.0 Pro, at 26.7. This view shows only models we track, each at its best.
- 1 GPT-4 (snapshot unspecified) 75.0
- 2 Gemini 1.5 Pro (snapshot unspecified) 61.1
- 3 GPT-4o (snapshot unspecified) 55.0
- 4 GPT-3.5 (snapshot unspecified) 38.5
- 5
Gemini 1.0 Pro 26.7
- 6 Gemini Flash 14.3
Source: The Werewolf Arena paper
Source: The Werewolf Arena paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-4 (snapshot unspecified) | 75.0 | Official leaderboard | ||
| 2 | Gemini 1.5 Pro (snapshot unspecified) | 61.1 | Official leaderboard | ||
| 3 | GPT-4o (snapshot unspecified) | 55.0 | Official leaderboard | ||
| 4 | GPT-3.5 (snapshot unspecified) | 38.5 | Official leaderboard | ||
| 5 | | 26.7 | Dec 2023 | Official leaderboard | |
| 6 | Gemini Flash | 14.3 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 26.7 | Dec 2023 | Official leaderboard |
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official Werewolf Arena leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
More in Games and long tasks
- ARC-AGI-3 In use Interactive game environments where agents must explore, infer goals and rules, and act efficiently without instructions. GPT-6.2 Astra 100%
- Orak Fading LLM agents play 12 popular video games across most genres through an MCP interface. Each game scores in-game progress or outcomes, and the board ranks models by their average rank across the games.
Gemini 2.5 Pro 3.90
- MineDojo Fading Agents complete open-ended tasks in Minecraft, such as mining blocks and fighting mobs, from a large simulation suite. Programmatic checks score many tasks.
Seed2.0 Pro 49%
- TextQuests Only in system cards Agents play 25 classic interactive fiction games. The score is harmful actions per 100 steps, where lower is better. The board also reports game progress.
Llama 4 Scout 7.00
- GameWorld Only in system cards Multimodal game agents play 34 browser games across 170 tasks. Outcomes are checked from the game state. GPT-6.1 Terra 76.8%
- Swarm Bench Only in system cards Models orchestrate agent swarms on complex tasks that benefit from coordinated decomposition and parallel execution. Kimi K3 76.3%
Data audit
8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 2 years ago, in December 2023, for Gemini 1.0 Pro. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
- Pass Independent runs Scores from the benchmark’s paper (6 entries).
- Pass Models scored 1 model we track, plus 5 other entries on its leaderboard.
- Warning Newest score The newest came 2 years ago, in December 2023, for Gemini 1.0 Pro.
- Note Frontier models None of its models are on the capabilities index.
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 1 row for models we track and 5 other entries at the last read.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.