PinpointQA - Structured Spatial Prediction: leaderboard

Structured spatial prediction on PinpointQA (2026): from 64 frames of an indoor ScanNet++ or ScanNet200 video, the model outputs the supporting surface, reference objects, relations and distances of a small object as JSON, scored programmatically and zero when no JSON is recoverable. Mean score scaled to 0-100; higher is better.

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. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1GPT-5.415#135
2Kimi K2.515#266
3Qwen 3 VL 8B Instruct12#1029
4SenseNova-SI-1.3-InternVL3-8B12#1610
5InternVL3.5-8B-Instruct9#1891
6LLaVA-OneVision-1.5-8B7#1864
7Cambrian-S-7B5#2198
8Spatial-MLLM-820K-4B0

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

Interactive version: theaggregate.ai/benchmark?slug=pinpointqa-structured-spatial-prediction · How It Works · Data refreshed daily, snapshot 2026-11-21.