OmniToM - Belief Labeling - Knowledge Access: leaderboard
Metric: Belief-labeling accuracy (%): exact-match accuracy of the predicted schema label on the given gold belief propositions, macro-averaged over stories, for the knowledge access (private, shared or public) dimension, on the 895 OmniToM stories from seven ToMBench categories (22,343 gold belief propositions), zero-shot TELeR level 3 prompts; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Mistral Small 3 | 74.59 |
| 2 | Mistral Large 2 (Jul) | 74.14 |
| 3 | Qwen 3 32B | 73.91 |
| 4 | Gemma 3 27B (IT) | 71.57 |
| 5 | Gemini 2.5 Flash | 71.34 |
| 6 | Llama 3.3 70B Instruct | 67.41 |
| 7 | GPT-5 | 66.85 |
| 8 | Qwen 3 8B | 57.94 |
| 9 | Llama 3.1 8B Instruct | 56.13 |
Interactive version: theaggregate.ai/benchmark?slug=omnitom-belief-labeling-knowledge-access · How It Works · Data refreshed daily, snapshot 2026-10-07.