GroupToM-Bench - Mechanistic Attribution: leaderboard
Metric: mean judge score (0-100) on Level 7 mechanistic attribution (structural explanation of a collective failure), open-ended, scored 0 to 100 by a GPT-5 judge against expert references; 240 multimodal multi-agent scenarios (scene image plus dialogue); higher is better. Source: arxiv.org. Saturation forecast: Around August 2027. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro | 64.2 |
| 2 | GPT-5 | 61 |
| 3 | GPT-5 Mini | 59.9 |
| 4 | GPT-4o | 53.4 |
| 5 | Claude Haiku 4.5 | 52.9 |
| 6 | GPT-5 Nano | 49 |
| 7 | InternVL3.5-8B | 47.5 |
| 8 | Qwen 2.5 VL 7B Instruct | 43.4 |
| 9 | Qwen 2 VL 7B | 41.3 |
Interactive version: theaggregate.ai/benchmark?slug=grouptom-bench-mechanistic-attribution · How It Works · Data refreshed daily, snapshot 2026-09-29.