AoPS Strategy Coverage - Geometry: leaderboard

The geometry problems of the AoPS strategy-coverage evaluation (Yang et al., 2026): the share of the 53 human solution-strategy families from Art of Problem Solving that a model recovers when asked for multiple distinct solutions per problem. Percent; higher is better.

Metric: AoPS-reference strategies recovered (% of the 53 reference strategy families for the 16 geometry problems; multiple-strategy prompt). Source: arxiv.org. Saturation forecast: Around February 2027. 4 models tracked.

Top models

#ModelScoreOverall rank
1Gemini 3.1 Pro (Preview)64.15#91
2GPT-5.452.83#121
3DeepSeek V3.2 (Thinking)49.06#403 (DeepSeek V3.2)
4Claude Opus 4.630.19#100

No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.

Interactive version: theaggregate.ai/benchmark?slug=aops-strategy-coverage-geometry · How It Works · Data refreshed daily, snapshot 2026-11-12.