TriViewBench - Object Counting: leaderboard
Metric: Accuracy (%) over the 7,692 Object Counting questions (objects visible in each view and in total), all four complexity levels; three orthographic views (front, side, top) of synthetic 3D tower scenes, direct prompting with a concise answer within 128 tokens, greedy decoding; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 18 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Flash | 78.59 |
| 2 | Claude 3.7 Sonnet | 68.23 |
| 3 | GPT-4o | 58.52 |
| 4 | Qwen 3 VL 32B Instruct | 56.94 |
| 5 | Qwen 3 VL 8B Instruct | 56.49 |
| 6 | Qwen 3 VL 4B Instruct | 47.2 |
| 7 | Qwen 2.5 VL 32B Instruct | 43.8 |
| 8 | Qwen 2.5 VL 7B Instruct | 35.06 |
| 9 | InternVL3.5-8B | 26.53 |
Interactive version: theaggregate.ai/benchmark?slug=triviewbench-object-counting · How It Works · Data refreshed daily, snapshot 2026-09-29.