Avalon-ToM-Bench - Tacit Coordination: leaderboard
Metric: Accuracy (%). Source: arxiv.org. 27 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro | 92.14 |
| 2 | GPT-5 | 91.43 |
| 3 | GPT-5 Mini | 89.29 |
| 4 | Gemini 2.5 Flash | 88.41 |
| 5 | Qwen 3 8B (Thinking) | 87.4 |
| 6 | Qwen 3 4B 2507 (Thinking) | 84.89 |
| 7 | Qwen 3 14B (Reasoning) | 83.45 |
| 8 | Phi-4 | 80 |
| 9 | Qwen 3.5 9B (Thinking) | 79.7 |
| 10 | Qwen 3 4B (Reasoning) | 78.03 |
| 11 | GPT-OSS-120B | 77.86 |
| 12 | GPT-4o Mini | 77.86 |
| 13 | Gemma 3 27B (IT) | 77.14 |
| 14 | Mistral 7B Instruct (v0.3) | 73.57 |
| 15 | Phi-3.5-mini-instruct | 72.86 |
Interactive version: theaggregate.ai/benchmark?slug=avalon-tom-bench-tacit-coordination · How It Works · Data refreshed daily, snapshot 2026-09-19.