AoPS Strategy Coverage - Probability: leaderboard
Metric: AoPS-reference strategies recovered (% of the 39 reference strategy families for the 16 probability problems; multiple-strategy prompt). Source: arxiv.org. Saturation forecast: Around December 2026. 4 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 79.49 |
| 2 | GPT-5.4 | 71.79 |
| 3 | DeepSeek V3.2 (Thinking) | 64.1 |
| 4 | Claude Opus 4.6 | 53.85 |
Interactive version: theaggregate.ai/benchmark?slug=aops-strategy-coverage-probability · How It Works · Data refreshed daily, snapshot 2026-09-26.