IDEAL-Bench - Geometric Reasoning: leaderboard
The geometric score of IDEAL-Bench (2026), a single-image 3D indoor layout benchmark: the unweighted mean of position accuracy, box precision and rotation accuracy in non-grid rooms and of grid coverage and grid self-consistency in classroom, library and office scenes, from 0 to 100. Higher is better.
Metric: Geometric score (0-100): unweighted mean of position accuracy, box precision and rotation accuracy (non-grid rooms) and grid coverage and grid self-consistency (classroom, library and office scenes) on the IDEAL-Bench 3D layout task; higher is better. Source: arxiv.org. Saturation forecast: Around 2028. 13 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Pro | 40.1 | #266 |
| 2 | GPT-4o | 35.9 | #741 |
| 3 | Gemma 4 31B (IT) | 35.7 | #342 |
| 4 | Claude Sonnet 4.6 | 34.7 | #161 |
| 5 | GLM-4.6V | 30.7 | #701 |
| 6 | Qwen 3 VL 8B Instruct | 28.6 | #981 |
| 7 | GPT-5.4 | 28.4 | #123 |
| 8 | Qwen 2.5 VL 72B Instruct | 27.9 | #846 |
| 9 | Qwen 3 VL 235B A22B Instruct | 24.3 | #522 |
| 10 | Qwen 3 VL 30B A3B Instruct | 22.6 | #871 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=ideal-bench-geometric-reasoning · How It Works · Data refreshed daily, snapshot 2026-11-13.