CurveBench - Hard: leaderboard
Metric: Tree-Generation Accuracy (%; exact containment tree, 456 polygon, topographic, maze and counting images, one rollout). Source: arxiv.org. Saturation forecast: Around September 2028. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 19.1 |
| 2 | GPT-5.4 | 6.6 |
| 3 | Claude Opus 4.5 | 4.2 |
| 4 | Qwen 3 VL 8B (Thinking) | 4.2 |
| 5 | GPT-5.4 Mini | 2.4 |
| 6 | Gemma 3 12B (IT) | 0.7 |
Interactive version: theaggregate.ai/benchmark?slug=curvebench-hard · How It Works · Data refreshed daily, snapshot 2026-09-25.