MalruleLib - Forward MRA: leaderboard
Metric: Forward MRA Accuracy (%; predict the student's answer from a description of the misconception). Source: arxiv.org. Saturation forecast: Around December 2026. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3 Next 80B A3B (Thinking) | 53.9 |
| 2 | GPT-OSS-120B | 48.8 |
| 3 | GPT-OSS-20B | 46.5 |
| 4 | Llama 3.3 70B Instruct | 39.6 |
| 5 | Phi-4 | 37.4 |
| 6 | Qwen 3 Next 80B A3B Instruct | 30.6 |
| 7 | Qwen 3 4B | 17.4 |
| 8 | Phi-4 Mini Instruct | 9.3 |
Interactive version: theaggregate.ai/benchmark?slug=malrulelib-forward-mra · How It Works · Data refreshed daily, snapshot 2026-09-25.