EnactToM: leaderboard
Theory of Mind (ToM), the ability to track others epistemic state, makes humans efficient collaborators. AI agents need the same capacity in multi agent settings, yet existing benchmarks mostly test literal ToM by asking direct belief questions. The ability act optimally on implicit beliefs in embodied environments, called functional ToM, remains largely untested. We introduce EnactToM, an evolvin
Metric: Avg Standard Functional (self-reported). Source: benchmarklist.com. 7 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.4 | 17.5 | #79 |
| 2 | O3 | 12.5 | #124 |
| 3 | GPT-5.4 Mini | 10.8 | #212 |
| 4 | Kimi K2.5 | 5.8 | #144 |
| 5 | DeepSeek V3.2 | 2.5 | #205 |
Interactive version: theaggregate.ai/benchmark?slug=enacttom · How It Works · Data refreshed daily, snapshot 2026-10-20.