Metacognitive Probe — leaderboard
Metric: Mean(T1,T2,T4,T5) (self-reported). Source: benchmarklist.com. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.6 | 82 |
| 2 | Claude Opus 4.6 | 80.75 |
| 3 | GLM-5 | 74.25 |
| 4 | Gemini 2.5 Pro | 74 |
| 5 | Gemma 3 27B | 70.5 |
| 6 | Gemini 2.5 Flash | 70.25 |
Interactive version: theaggregate.ai/benchmark?slug=metacognitive-probe · How the rankings work · Data refreshed daily, snapshot 2026-07-22.