SSMNBench - Multi-View Necessity: leaderboard
Metric: Mean accuracy (%) over the six multi-view-necessity tasks (distinct human counting, counting with attribute, relative cross-person pose, relative distance, global orientation, global depth ordering), where no single view suffices; four-option multiple choice on dense, occlusion-heavy multi-view scenes of people, given exactly the annotated necessary views (the +0 setting); 300 questions per task, images resized to 1920x1080, single-letter answers. Source: arxiv.org. Saturation forecast: Around 2030. 16 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro | 44 |
| 2 | GPT-5.2 | 42.4 |
| 3 | Gemini 2.5 Flash | 39.4 |
| 4 | InternVL3-78B | 39.3 |
| 5 | Qwen 2.5 VL 32B Instruct | 38.9 |
| 6 | Qwen 2.5 VL 72B Instruct | 38.3 |
| 7 | Qwen 2.5 VL 7B Instruct | 35.3 |
Interactive version: theaggregate.ai/benchmark?slug=ssmnbench-multi-view-necessity · How It Works · Data refreshed daily, snapshot 2026-09-29.