---
title: Metacognition Leaderboard
emoji: 🧠
colorFrom: indigo
colorTo: pink
sdk: docker
app_port: 7860
pinned: false
license: apache-2.0
---

# 🧠 Metacognition Leaderboard

Live, visual leaderboard for **[ginigen-ai/Metacognition-Bench](https://huggingface.co/datasets/ginigen-ai/Metacognition-Bench)**.

33 LLMs ranked by **metacognitive vulnerability** (`trap_rate`): given a 4-choice version of each trap problem (correct option + a seductive trap distractor), how often the model fails to pick the correct answer. Lower = stronger metacognition.

- Benchmark: [Metacognition-Bench](https://huggingface.co/datasets/ginigen-ai/Metacognition-Bench)
- Data: [Metacognition-Leaderboard](https://huggingface.co/datasets/ginigen-ai/Metacognition-Leaderboard)
- Curated by **ginigen-ai (VIDRAFT)** · Adapter: AETHER Metacognition Adapter (proprietary)