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

#ModelScore
1GPT-5.276.5
2GLM-576.38
3Claude Opus 4.676.17
4GPT-OSS-120B73.33
5DeepSeek V3.273.08

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