Beyond Survival
Models play social deduction games with human-aligned strategies and interaction patterns.
The 2026 EMNLP paper compares multiple language models in social deduction games. The checked page does not state the best score.
- Made by
- Beyond Survival authors
- Released
- November 2026
- 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
- Strongest model tested
- GPT-5 #71 on the capability index
- Last model added
- September 2025
- Scores refreshed
- November 21st, 2026
Gemini-2.5-pro (snapshot unspecified) tops the leaderboard with 71.5% GPT-5 leads with 58.7% among models released by September 2025
Best score per entry from the benchmark's paper, read on November 21st, 2026. A paper’s table doesn’t add newer models. 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 GPT-5, at 58.7%. This view shows only models we track, each at its best.
The newest model with a score here came out in September 2025, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 71.5 Gemini-2.5-pro (snapshot unspecified)
- 59.0 Deepseek-R1 (snapshot unspecified)
- 58.7 GPT-5
- 57.3 GLM-4.5
- 56.5
DeepSeek-V3.2-Exp
- 55.8
Gemini 2.5 Flash
- 52.0
DeepSeek-V3.1
- 48.8 GPT-5 mini
- 45.6
QwQ-32B
- 45.0
Llama 4 Scout
- 44.6
Qwen3-32B
- 43.1
Qwen3-30B-A3B
- 35.8 gpt-oss-20b
- 34.9
Gemma 3 27B
- 31.1 GPT-5 nano
- 1 Gemini-2.5-pro (snapshot unspecified) 71.5%
- 2 Deepseek-R1 (snapshot unspecified) 59%
- 3 GPT-5 58.7%
- 4 GLM-4.5 57.3%
- 5
DeepSeek-V3.2-Exp 56.5%
- 6
Gemini 2.5 Flash Sep 2025 55.8%
- 7
DeepSeek-V3.1 52%
- 8 GPT-5 mini 48.8%
- 9
QwQ-32B 45.6%
- 10
Llama 4 Scout 45%
- 11
Qwen3-32B 44.6%
- 12
Qwen3-30B-A3B 43.1%
- 13 gpt-oss-20b 35.8%
- 14
Gemma 3 27B 34.9%
- 15 GPT-5 nano 31.1%
Source: The Beyond Survival paper
- 1 GPT-5 58.7%
- 2 GLM-4.5 57.3%
- 3
DeepSeek-V3.2-Exp 56.5%
- 4
Gemini 2.5 Flash Sep 2025 55.8%
- 5
DeepSeek-V3.1 52%
- 6 GPT-5 mini 48.8%
- 7
QwQ-32B 45.6%
- 8
Llama 4 Scout 45%
- 9
Qwen3-32B 44.6%
- 10
Qwen3-30B-A3B 43.1%
- 11 gpt-oss-20b 35.8%
- 12
Gemma 3 27B 34.9%
- 13 GPT-5 nano 31.1%
Source: The Beyond Survival paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Gemini-2.5-pro (snapshot unspecified) | 71.5% | Official leaderboard | ||
| 2 | Deepseek-R1 (snapshot unspecified) | 59% | Official leaderboard | ||
| 3 | GPT-5 | 58.7% | Aug 2025 | Official leaderboard | |
| 4 | GLM-4.5 | 57.3% | Aug 2025 | Official leaderboard | |
| 5 | | 56.5% | Sep 2025 | Official leaderboard | |
| 6 | | 55.8% | Sep 2025 | Official leaderboard | |
| 7 | | 52% | Aug 2025 | Official leaderboard | |
| 8 | GPT-5 mini | 48.8% | Aug 2025 | Official leaderboard | |
| 9 | | 45.6% | Mar 2025 | Official leaderboard | |
| 10 | | 45% | Apr 2025 | Official leaderboard | |
| 11 | | 44.6% | Apr 2025 | Official leaderboard | |
| 12 | | 43.1% | Apr 2025 | Official leaderboard | |
| 13 | gpt-oss-20b | 35.8% | Aug 2025 | Official leaderboard | |
| 14 | | 34.9% | Mar 2025 | Official leaderboard | |
| 15 | GPT-5 nano | 31.1% | Aug 2025 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-5 | 58.7% | Aug 2025 | Official leaderboard | |
| 2 | GLM-4.5 | 57.3% | Aug 2025 | Official leaderboard | |
| 3 | | 56.5% | Sep 2025 | Official leaderboard | |
| 4 | | 55.8% | Sep 2025 | Official leaderboard | |
| 5 | | 52% | Aug 2025 | Official leaderboard | |
| 6 | GPT-5 mini | 48.8% | Aug 2025 | Official leaderboard | |
| 7 | | 45.6% | Mar 2025 | Official leaderboard | |
| 8 | | 45% | Apr 2025 | Official leaderboard | |
| 9 | | 44.6% | Apr 2025 | Official leaderboard | |
| 10 | | 43.1% | Apr 2025 | Official leaderboard | |
| 11 | gpt-oss-20b | 35.8% | Aug 2025 | Official leaderboard | |
| 12 | | 34.9% | Mar 2025 | Official leaderboard | |
| 13 | GPT-5 nano | 31.1% | Aug 2025 | Official leaderboard |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: The Beyond Survival paper
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official Beyond Survival 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
9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 14 months ago, in September 2025, for DeepSeek-V3.2-Exp. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 3 pass 1 note
- Pass Independent runs Scores from the benchmark’s paper (15 entries).
- Pass Models scored 13 models we track, plus 2 other entries on its leaderboard.
- Warning Newest score The newest came 14 months ago, in September 2025, for DeepSeek-V3.2-Exp.
- Note Frontier models None of the top 10 has a score. The strongest tested is GPT-5 (#71).
- Pass Headroom The best is 58.7%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on aclanthology.org: 13 rows for models we track and 2 other entries at the last read.
- Pass Last read November 21st, 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.