QMFOLBench: leaderboard
Metric: Macro-F1 (%; True, False and Unknown labels, 2,880 tasks). Source: arxiv.org. Saturation forecast: Estimated already saturated. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) (High) | 99.03 |
| 2 | GPT-5.4 (High) | 97.4 |
| 3 | Qwen 3.5 27B (Thinking) | 92.19 |
| 4 | DeepSeek V3.2 (Thinking) | 90.77 |
| 5 | Claude Sonnet 4.6 (Thinking) | 79.7 |
| 6 | DeepSeek V3.2 (Non-reasoning) | 76.27 |
| 7 | Qwen 3 32B (Thinking) | 63.29 |
| 8 | GPT-5.4 (Non-reasoning) | 55.08 |
Interactive version: theaggregate.ai/benchmark?slug=qmfolbench · How It Works · Data refreshed daily, snapshot 2026-09-25.