ParliamentBench
Models play Secret Hitler while deceiving, persuading, and reasoning under hidden roles.
The July 2026 paper evaluates 16 language models across 1,600 simulated matches. The abstract does not state the best score.
- Made by
- ParliamentBench authors
- Released
- July 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
- Secret Hitler
- Items from
- Live play or votes, Generated
- Refresh
- Live
- Run by
- Anyone
- In views
- Games, Agents, Kept fresh
- Strongest model tested
- GPT-5.4 #28 on the capability index
- Last model added
- March 2026
- Scores refreshed
- November 20th, 2026
GPT-5.4 leads with 81% among models released by March 2026
Best score per model from the benchmark's own leaderboard, read on November 20th, 2026. The score is the percentage of games the model won against Llama 3.3 70B opponents. Where a model ran with several settings or harnesses, we keep its best.
The newest model with a score here came out in March 2026, 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
- 1 GPT-5.4 81%
- 2 Kimi K2.5 76%
- 3 Grok 4.1 Fast 69%
- 4
DeepSeek-V3.1-Terminus 66%
- 5
Llama 3.3 70B 57.6%
- 6
Qwen3.5 397B-A17B 56%
- 7
Olmo 3.1 32B Instruct 53%
- 8 gpt-oss-120b 50%
- 9
Mistral Small 3 43%
- 10
Llama 3.1-70B 42%
- 11
Gemma 3 27B 39%
- 12 gpt-oss-20b 24%
Source: Official ParliamentBench leaderboard
| # | Model | Score ± | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-5.4 | 81% 73 to 88 | Mar 2026 | Official leaderboard | |
| 2 | Kimi K2.5 | 76% 67 to 84 | Jan 2026 | Official leaderboard | |
| 3 | Grok 4.1 Fast | 69% ±9 | Nov 2025 | Official leaderboard | |
| 4 | | 66% ±9 | Sep 2025 | Official leaderboard | |
| 5 | | 57.6% 48.5 to 65.7 | Dec 2024 | Official leaderboard | |
| 6 | | 56% ±10 | Feb 2026 | Official leaderboard | |
| 7 | | 53% 44 to 63 | Dec 2025 | Official leaderboard | |
| 8 | gpt-oss-120b | 50% ±10 | Aug 2025 | Official leaderboard | |
| 9 | | 43% ±10 | Jan 2025 | Official leaderboard | |
| 10 | | 42% ±9 | Jul 2024 | Official leaderboard | |
| 11 | | 39% ±9 | Mar 2025 | Official leaderboard | |
| 12 | gpt-oss-20b | 24% 16 to 33 | Aug 2025 | Official leaderboard |
Rankings by part
We read 3 parts from the benchmark’s own leaderboard: Liberal, Fascist and Hitler. Each ranks models on one part of the test. GPT-5.4 leads 2 of them, and Kimi K2.5 leads the other one. Arrows show how far a model moved from its overall rank among the models we track.
Liberal
12 models we track have a score here.
- 1 GPT-5.4 81.7%
- 2
DeepSeek-V3.1-Terminus ↑2 76.7%
- 3 Grok 4.1 Fast 75%
- 4
Llama 3.3 70B ↑1 74.6%
- 5 Kimi K2.5 ↓3 73.3%
- 6
Qwen3.5 397B-A17B 60%
- 7
Llama 3.1-70B ↑3 55%
- 8
Olmo 3.1 32B Instruct ↓1 55%
- 9
Mistral Small 3 45%
- 10
Gemma 3 27B ↑1 45%
Fascist
12 models we track have a score here.
- 1 Kimi K2.5 ↑1 85%
- 2 GPT-5.4 ↓1 80%
- 3 Grok 4.1 Fast 70%
- 4
DeepSeek-V3.1-Terminus 50%
- 5
Qwen3.5 397B-A17B ↑1 50%
- 6
Mistral Small 3 ↑3 45%
- 7
Olmo 3.1 32B Instruct 45%
- 8 gpt-oss-120b 40%
- 9 gpt-oss-20b ↑3 35%
- 10
Gemma 3 27B ↑1 30%
Hitler
12 models we track have a score here.
- 1 GPT-5.4 80%
- 2 gpt-oss-120b ↑6 75%
- 3 Kimi K2.5 ↓1 75%
- 4
Olmo 3.1 32B Instruct ↑3 55%
- 5
DeepSeek-V3.1-Terminus ↓1 50%
- 6 Grok 4.1 Fast ↓3 50%
- 7
Qwen3.5 397B-A17B ↓1 50%
- 8
Llama 3.3 70B ↓3 45%
- 9
Llama 3.1-70B ↑1 35%
- 10
Mistral Small 3 ↓1 35%
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official ParliamentBench 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 ParliamentBench 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 8 months ago, in March 2026, for GPT-5.4. 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 official leaderboard (12 entries).
- Pass Models scored 12 models we track.
- Warning Newest score The newest came 8 months ago, in March 2026, for GPT-5.4.
- Note Frontier models None of the top 10 has a score. The strongest tested is GPT-5.4 (#28).
- Pass Headroom The best is 81%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on github.com: 12 rows for models we track 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.