3D Scene Structure - Single-Object Removal: leaderboard

Metric: Correctness (%, human-scored; 602 scenes; correct only with complete recall of the newly visible objects and nothing invented). Source: arxiv.org. Saturation forecast: Around 2032. 6 models tracked.

Top models

#ModelScore
1GPT-5.2 (Thinking)23.01
2Qwen 3.5 397B A17B (Thinking)22.85
3Qwen 3 VL 30B A3B (Thinking)21.03
4Qwen 3 VL 8B (Thinking)14.9

Interactive version: theaggregate.ai/benchmark?slug=3d-scene-structure-single-object-removal · How It Works · Data refreshed daily, snapshot 2026-09-25.