OmniToM: leaderboard
Theory of Mind (ToM), the ability to infer others' knowledge, intentions, and emotions, is commonly evaluated in large language models (LLMs) using end-point question answering, where performance is judged solely by the final answer to a social reasoning query. This paradigm obscures whether the model actually constructs the underlying mental-state representations required for robust reasoning, pa
Metric: Stage 2 Overall Acc (self-reported). Source: benchmarklist.com. Saturation forecast: Around November 2026. 9 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Flash | 85.95 | #245 |
| 2 | GPT-5 | 82.85 | #98 |
| 3 | Llama 3.3 70B | 79.55 | #579 |
| 4 | Qwen 3 32B | 79.16 | #443 |
| 5 | Gemma 3 27B | 78.46 | #607 |
| 6 | Qwen 3 8B | 64.26 | #674 |
| 7 | Llama 3.1 8B | 62.66 | #1151 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=omnitom · How It Works · Data refreshed daily, snapshot 2026-10-20.