OmniToM - Belief Labeling - Knowledge Access: leaderboard

OmniToM (2026) evaluates theory of mind through explicit belief modeling on 895 short social stories from ToMBench, with gold belief propositions built by a human-calibrated annotation pipeline. This board is Stage 2 labeling accuracy for the knowledge access (private, shared or public) dimension of the given belief propositions; higher is better.

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 February 2027. 9 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Mistral Small 374.59#1809
2Mistral Large 2 (Jul)74.14#1164
3Qwen 3 32B73.91#983
4Gemma 3 27B (IT)71.57#1341
5Gemini 2.5 Flash71.34#466
6Llama 3.3 70B Instruct67.41#1394
7GPT-566.85#185
8Qwen 3 8B57.94#1890
9Llama 3.1 8B Instruct56.13#4655

No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=omnitom-belief-labeling-knowledge-access · How It Works · Data refreshed daily, snapshot 2026-11-22.