PointQ-Bench - Usability Grading: leaderboard

Three-level usability grading of point clouds on 3,083 point clouds from real scans, simulated distortions and AI-generated assets (PointQ-Bench, 2026), with 2D models seeing six rendered views and 3D models sampled points. Macro-F1 in percent; higher is better.

Metric: Macro-F1 (%) of the three-level usability decision, zero-shot over 3,083 point clouds (authentic scans, simulated distortions, AI-generated assets), temperature 0; 2D models see six rendered views, native 3D models 8,192 sampled points; free-form answers mapped to the label space by an LLM parser; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 13 models tracked. Updated 7 Oct 2026.

Top models

#ModelSettingScoreOverall rank
1GPT-5Low50.13#178
2Qwen 3.5 27BNon-reasoning46.05#375
3GPT-5 MiniLow40.91#364
4Mistral Small 3.238.56#1641
5InternVL3.5-8B38.28#1604
6InternVL3.5-14B35.83#1504
7PointLLM-13B35.64
8Claude Haiku 4.534.4#583
9PointLLM-7B34.08
10ShapeLLM-13B25.01
11Qwen 3.5 9BNon-reasoning24.68#828
12ShapeLLM-7B24.18
13Gemma 3 12B18.5#2059

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=pointq-bench-usability-grading · How It Works · Data refreshed daily, snapshot 2026-11-21.