GeoChallenge (Text Only) - Medium: leaderboard
Metric: Exact match in percent on the Medium split on GeoChallenge-small (908 multiple-choice geometry proof problems sampled to match the full set's difficulty profile; one or more correct options per problem), unified prompt, greedy decoding (temperature 0), 16,384 output tokens, no tools; a problem counts only when the selected option set equals the gold set (no-guess protocol), with the problem text only (no diagram); higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 10 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3 235B A22B 2507 (Thinking) | 75.95 | #253 (Qwen 3 235B A22B 2507) |
| 2 | O3 Mini (2025-01-31) | 69.04 | #232 |
| 3 | O3 (2025-04-16) | 60.8 | #117 |
| 4 | Gemini 3 Pro (Preview) | 49 | #64 |
| 5 | Claude Sonnet 4.5 (Thinking) | 34.3 | #138 (Claude Sonnet 4.5) |
| 6 | DeepSeek R1 0528 | 16.7 | #217 |
| 7 | Claude 3.5 Sonnet | 15.37 | #337 |
| 8 | Gemini 1.5 Pro | 14.7 | #442 |
| 9 | GPT-4o | 8.69 | #333 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=geochallenge-text-only-medium · How It Works · Data refreshed daily, snapshot 2026-10-11.