LemmaBench (April 2026, Gemini 3.1 Pro Judge): leaderboard
Metric: Proof acceptance rate (%): share of the April 2026 batch's research-level lemmas (120 self-contained lemmas extracted by GPT-5.5 from 31 late-April arXiv preprints; DeepSeek-R1's rate is over 110) whose single generated natural-language proof the Gemini 3.1 Pro judge accepts as a whole-proof verdict; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 3 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.5 | 65.8 | #26 |
| 2 | DeepSeek R1 | 51.8 | #245 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=lemmabench-april-2026-gemini-3-1-pro-judge · How It Works · Data refreshed daily, snapshot 2026-10-11.