OmniToM - Belief Labeling - Representation: 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 representation (explicitly stated or implicitly inferred) 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 representation (explicitly stated or implicitly inferred) 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
1Gemini 2.5 Flash87.58#463
2GPT-583.42#178
3Mistral Large 2 (Jul)72.87#1144
4Llama 3.3 70B Instruct72.43#1385
5Llama 3.1 8B Instruct64.4#4600
6Qwen 3 8B63.77#1873
7Mistral Small 362.79#1796
8Qwen 3 32B62.45#972
9Gemma 3 27B (IT)54.33#1324

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=omnitom-belief-labeling-representation · How It Works · Data refreshed daily, snapshot 2026-11-21.