Metacognitive Probe: leaderboard
The Metacognitive Probe is an exploratory five-task, 15-slot diagnostic that decomposes an LLM's confidence behaviour into five behaviourally-distinct dimensions: confidence calibration (T1-CC), epistemic vigilance (T2-EV), knowledge boundary (T3-KB), calibration range (T4-CR), and reasoning-chain validation (T5-RCV). It is evaluated on N=8 frontier models and N=69 humans. The instrument is motiva
Metric: Mean(T1,T2,T4,T5) (self-reported). Source: benchmarklist.com. Saturation forecast: Around June 2027. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Sonnet 4.6 | 82 | #90 |
| 2 | Claude Opus 4.6 | 80.75 | #63 |
| 3 | GLM-5 | 74.25 | #141 |
| 4 | Gemini 2.5 Pro | 74 | #152 |
| 5 | Gemma 3 27B | 70.5 | #607 |
| 6 | Gemini 2.5 Flash | 70.25 | #245 |
| 7 | DeepSeek R1 | 63.75 | #251 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=metacognitive-probe · How It Works · Data refreshed daily, snapshot 2026-10-20.