AdvancedMathBench - ProverBench Qualifying Exam: leaderboard
Metric: Proof acceptance rate (%) on the 45 doctoral qualifying-exam problems (QE split): temperature 1.0, 64k maximum output tokens, highest available reasoning effort; each proof is accepted only if all 8 parallel passes of the authors' expert-trained automatic verifier accept it (pessimistic verification); higher is better. Source: arxiv.org. Saturation forecast: Around January 2028. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 (xHigh) | 48.9 |
| 2 | GPT-5.5 (High) | 46.1 |
| 3 | DeepSeek V4 Pro (Max) | 40 |
| 4 | Claude Opus 4.8 (Max) | 40 |
| 5 | Qwen 3.5 397B A17B | 33.5 |
| 6 | GLM-5.2 (Max) | 28.9 |
| 7 | GPT-5.2 (xHigh) | 26.7 |
| 8 | Gemini 3.1 Pro (Preview) (High) | 17.8 |
| 9 | GPT-OSS-120B (High) | 2.2 |
Interactive version: theaggregate.ai/benchmark?slug=advancedmathbench-proverbench-qualifying-exam · How It Works · Data refreshed daily, snapshot 2026-09-29.