PinpointQA - Nearest Reference Identification: leaderboard
Nearest reference identification on PinpointQA (2026): from 64 frames of an indoor ScanNet++ or ScanNet200 video, the model picks which of four objects is nearest to a small target, not counting its supporting surface. Exact-match accuracy scaled to 0-100; higher is better.
Metric: Exact-match accuracy (times 100, micro over QA pairs) of four-option nearest reference object identification (excluding the supporting surface) 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 July 2028. 8 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Kimi K2.5 | 42 | #272 |
| 2 | GPT-5.4 | 39 | #138 |
| 3 | Qwen 3 VL 8B Instruct | 37 | #1043 |
| 4 | InternVL3.5-8B-Instruct | 36 | #1911 |
| 5 | SenseNova-SI-1.3-InternVL3-8B | 36 | #1627 |
| 6 | Cambrian-S-7B | 33 | #2216 |
| 7 | LLaVA-OneVision-1.5-8B | 30 | #1876 |
| 8 | Spatial-MLLM-820K-4B | 30 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=pinpointqa-nearest-reference-identification · How It Works · Data refreshed daily, snapshot 2026-11-22.