PinpointQA - Structured Spatial Prediction: leaderboard
Metric: Structured spatial prediction score (times 100, micro over QA pairs): programmatic weighted score of supporting surface, reference objects, relations and distances in a recovered JSON prediction (zero when no JSON is recoverable) of the PinpointQA evaluation split (2,019 QA pairs from held-out ScanNet++ and ScanNet200 scenes; 64 uniformly sampled RGB frames per indoor video, no depth or 3D input, greedy decoding); higher is better. Source: arxiv.org. Saturation forecast: Around 2029. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.4 | 15 |
| 2 | Kimi K2.5 | 15 |
| 3 | Qwen 3 VL 8B Instruct | 12 |
Interactive version: theaggregate.ai/benchmark?slug=pinpointqa-structured-spatial-prediction · How It Works · Data refreshed daily, snapshot 2026-10-07.