Skip to content

The Aggregate

Unified LLM rankings, daily

Models What's New Trends Benchmarks Skill Maps
How It Works Guesswork Metrics
The Aggregate
Loading data...

MMToM-QA - Belief — leaderboard

Metric: Belief (%). Source: chuanyangjin.com. 15 models tracked.

Top models

#ModelScore
1O3 Mini88.7
2Gemini 2.0 Flash (Thinking)73.3
3Gemini 2.0 Flash62.7
4GPT-4o55.7
5Llama 3.1 70B51.3

Interactive version: theaggregate.ai/benchmark?slug=mmtom-qa-belief · How the rankings work · Data refreshed daily, snapshot 2026-07-22.

Built by Mikhail Doroshenko — AI researcher, co-author of Humanity’s Last Exam. Independent project; no affiliation with any AI lab.