PointQ-Bench - Quality Reasoning: leaderboard
Open-ended point-cloud quality reports 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, scored 0-10 as the sum of five 0-2 judge ratings (structure, specificity, faithfulness, coherence, quality accuracy) against an expert reference. Higher is better.
Metric: SSFRQ-5D score (0-10): sum of five 0-2 judge ratings (structural sufficiency, specificity, faithfulness, reasoning coherence, quality accuracy) of the open-ended quality report against an expert reference, 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. 14 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | GPT-5 | Low | 8.41 | #178 |
| 2 | GPT-5 Mini | Low | 8.21 | #364 |
| 3 | Qwen 3.5 9B | Non-reasoning | 7.89 | #828 |
| 4 | Gemma 3 12B | 7.77 | #2059 | |
| 5 | Qwen 3.5 27B | Non-reasoning | 7.77 | #375 |
| 6 | Claude Haiku 4.5 | 7.76 | #583 | |
| 7 | InternVL3.5-14B | 7.76 | #1504 | |
| 8 | Mistral Small 3.2 | 7.73 | #1641 | |
| 9 | InternVL3.5-8B | 7.72 | #1604 | |
| 10 | ShapeLLM-13B | 6.32 | ||
| 11 | ShapeLLM-7B | 5.93 | ||
| 12 | PointLLM-13B | 4.49 | ||
| 13 | PointLLM-7B | 4.31 | ||
| 14 | MiniGPT-3D | 3 |
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-quality-reasoning · How It Works · Data refreshed daily, snapshot 2026-11-21.