FINAL Bench Metacognitive — leaderboard
FINAL Bench Metacognitive evaluates model capability on intelligence & reasoning tasks from the linked upstream source with Metacognitive Score as the primary reported metric.
Metric: Metacognitive Score (self-reported). Source: benchmarklist.com. Status: saturation imminent. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.2 | 76.5 |
| 2 | GLM-5 | 76.38 |
| 3 | Claude Opus 4.6 | 76.17 |
| 4 | GPT-OSS-120B | 73.33 |
| 5 | DeepSeek V3.2 | 73.08 |
Interactive version: theaggregate.ai/benchmark?slug=final-bench-metacognitive · How the rankings work · Data refreshed daily, snapshot 2026-07-22.