MineAmongUs
Vision-language agents play an embodied Among Us game with verbal and nonverbal deception.
The August 2026 paper compares multiple VLM agents. The abstract does not state the best score.
- Made by
- MineAmongUs authors
- Released
- August 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
- Among Us
- Items from
- Live play or votes
- Refresh
- Live
- Run by
- Anyone
- In views
- Games, Agents, Vision, Kept fresh
- Strongest model tested
-
Gemini 3 Flash #60 on the capability index
- Last model added
- April 2026
- Scores refreshed
- November 20th, 2026
Gemini 3 Flash leads with 81.3% among models released by April 2026
Best score per model from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. The headline is the mean of imposter and crewmate win rates against the same twelve opponents. Where a model ran with several settings or harnesses, we keep its best. Every run is in the next chart.
The newest model with a score here came out in April 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
Gemini 3 Flash Case1B 81.3%
- 2
Gemini 3.1 Flash-Lite Case2A 77.1%
- 3 GPT-4.1 mini Case2A 70.8%
- 4 GPT-5 mini Case2A 70.8%
- 5 Kimi K2.5 Case1B 64.6%
- 6
Gemma 4 31B IT Case1B 62.5%
- 7
Qwen3.5-27B Case2B 58.3%
- 8
Qwen3.6 27B Case2B 56.3%
- 9
Gemma 4 26B A4B Case1B 47.9%
- 10 GPT-5 Case2A 43.8%
- 11
Gemini 2.5 Flash Sep 2025, Case2A 37.5%
- 12
Qwen3.5-9B Case1B 22.9%
Source: The MineAmongUs paper
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 81.3% | Case1B, ARIA | Dec 2025 | Official leaderboard |
| 2 | | 77.1% | Case2A, ARIA | Mar 2026 | Official leaderboard |
| 3 | GPT-4.1 mini | 70.8% | Case2A, ARIA | Apr 2025 | Official leaderboard |
| 4 | GPT-5 mini | 70.8% | Case2A, ARIA | Aug 2025 | Official leaderboard |
| 5 | Kimi K2.5 | 64.6% | Case1B, ARIA | Jan 2026 | Official leaderboard |
| 6 | | 62.5% | Case1B, ARIA | Apr 2026 | Official leaderboard |
| 7 | | 58.3% | Case2B, ARIA | Feb 2026 | Official leaderboard |
| 8 | | 56.3% | Case2B, ARIA | Apr 2026 | Official leaderboard |
| 9 | | 47.9% | Case1B, ARIA | Apr 2026 | Official leaderboard |
| 10 | GPT-5 | 43.8% | Case2A, ARIA | Aug 2025 | Official leaderboard |
| 11 | | 37.5% | Case2A, ARIA | Sep 2025 | Official leaderboard |
| 12 | | 22.9% | Case1B, ARIA | Feb 2026 | Official leaderboard |
Rankings by part
We read 2 parts from the benchmark’s paper: Imposter win rate and Crewmate win rate. Each ranks models on one part of the test. Gemini 3 Flash leads both. Arrows show how far a model moved from its overall rank among the models we track.
Imposter win rate
12 models we track have a score here.
- 1
Gemini 3 Flash 83.3%
- 2 Kimi K2.5 ↑3 70.8%
- 3
Qwen3.5-27B ↑4 70.8%
- 4
Gemini 3.1 Flash-Lite ↓2 70.8%
- 5 GPT-4.1 mini ↓2 66.7%
- 6 GPT-5 ↑4 66.7%
- 7 GPT-5 mini ↓3 66.7%
- 8
Qwen3.6 27B 62.5%
- 9
Gemma 4 31B IT ↓3 58.3%
- 10
Gemini 2.5 Flash Sep 2025 ↑1 54.2%
Crewmate win rate
12 models we track have a score here.
- 1
Gemini 3 Flash 95.8%
- 2
Gemini 3.1 Flash-Lite 87.5%
- 3 GPT-5 mini ↑1 83.3%
- 4 GPT-4.1 mini ↓1 75%
- 5
Gemma 4 31B IT ↑1 75%
- 6 Kimi K2.5 ↓1 70.8%
- 7
Gemma 4 26B A4B ↑2 66.7%
- 8
Qwen3.6 27B 54.2%
- 9
Qwen3.5-27B ↓2 50%
- 10 GPT-5 37.5%
Scores at each effort level
Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.
Source: The MineAmongUs paper
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| Case1B | ARIA | 81.3% | |||
| Case2B | ARIA | 81.3% | |||
| Case1A | ARIA | 79.2% | |||
| Case2A | ARIA | 77.1% | |||
| Case1A | ARIA | 75% | |||
| GPT-4.1 mini | Case2A | ARIA | 70.8% | ||
| GPT-5 mini | Case2A | ARIA | 70.8% | ||
| Case1B | ARIA | 68.8% | |||
| Case2B | ARIA | 66.7% | |||
| Case2A | ARIA | 64.6% | |||
| Kimi K2.5 | Case1B | ARIA | 64.6% | ||
| GPT-4.1 mini | Case1B | ARIA | 62.5% | ||
| Kimi K2.5 | Case2A | ARIA | 62.5% | ||
| Kimi K2.5 | Case2B | ARIA | 62.5% | ||
| Case1B | ARIA | 62.5% | |||
| Case1A | ARIA | 60.4% | |||
| GPT-4.1 mini | Case1A | ARIA | 58.3% | ||
| Case2B | ARIA | 58.3% | |||
| GPT-5 mini | Case2B | ARIA | 56.3% | ||
| Kimi K2.5 | Case1A | ARIA | 56.3% | ||
| Case2B | ARIA | 56.3% | |||
| GPT-4.1 mini | Case2B | ARIA | 54.2% | ||
| Case1A | ARIA | 54.2% | |||
| Case1B | ARIA | 54.2% | |||
| Case1B | ARIA | 47.9% | |||
| Case1A | ARIA | 45.8% | |||
| Case1A | ARIA | 45.8% | |||
| GPT-5 | Case2A | ARIA | 43.8% | ||
| Case2A | ARIA | 43.8% | |||
| GPT-5 | Case1A | ARIA | 39.6% | ||
| GPT-5 | Case1B | ARIA | 39.6% | ||
| Case2B | ARIA | 39.6% | |||
| Case2A | ARIA | 39.6% | |||
| GPT-5 | Case2B | ARIA | 37.5% | ||
| Case2A | ARIA | 37.5% | |||
| Case2B | ARIA | 37.5% | |||
| Case1B | ARIA | 35.4% | |||
| Case1B | ARIA | 35.4% | |||
| Case2A | ARIA | 35.4% | |||
| Case2A | ARIA | 35.4% | |||
| GPT-5 mini | Case1A | ARIA | 33.3% | ||
| Case1A | ARIA | 33.3% | |||
| Case2B | ARIA | 27.1% | |||
| GPT-5 mini | Case1B | ARIA | 25% | ||
| Case1B | ARIA | 22.9% | |||
| Case2B | ARIA | 22.9% | |||
| Case1A | ARIA | 18.8% | |||
| Case2A | ARIA | 18.8% |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: The MineAmongUs 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 MineAmongUs 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 7 months ago, in April 2026, for Qwen3.6 27B. 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 (12 entries).
- Pass Models scored 12 models we track.
- Warning Newest score The newest came 7 months ago, in April 2026, for Qwen3.6 27B.
- Note Frontier models None of the top 10 has a score. The strongest tested is Gemini 3 Flash (#60).
- Pass Headroom The best is 81.3%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 48 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.