IDEAL-Bench - Geometric Reasoning: leaderboard

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 2030. 13 models tracked.

Top models

#ModelScore
1Gemini 2.5 Pro40.1
2GPT-4o35.9
3Gemma 4 31B (IT)35.7
4Claude Sonnet 4.634.7
5GLM-4.6V30.7
6Qwen 3 VL 8B Instruct28.6
7GPT-5.428.4
8Qwen 2.5 VL 72B Instruct27.9
9InternVL3.5-8B27
10Qwen 3 VL 235B A22B Instruct24.3
11Qwen 3 VL 30B A3B Instruct22.6

Interactive version: theaggregate.ai/benchmark?slug=ideal-bench-geometric-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-29.