OpenVLM MMT-Bench - Depth Estimation — leaderboard
Metric: Score (%). Source: huggingface.co. 207 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Ovis2-8B | 80 |
| 2 | Qwen 2 VL 72B | 75 |
| 3 | Qwen 2 VL 7B | 70 |
| 4 | InternVL3-38B | 70 |
| 5 | InternVL3-14B | 70 |
| 6 | Grok 2 (1212) | 60 |
| 7 | Gemini 1.5 Flash | 60 |
| 8 | Aquila-VL-2B | 45 |
| 9 | InternVL3-8B | 40 |
| 10 | InternVL3-78B | 30 |
| 11 | MiniCPM-V-2.6 | 30 |
| 12 | Gemma 3 27B | 30 |
| 13 | Pixtral-12B | 25 |
| 14 | Gemini 1.5 Pro | 25 |
| 15 | Gemma 3 12B | 25 |
Interactive version: theaggregate.ai/benchmark?slug=openvlm-mmt-bench-depth-estimation · How the rankings work · Data refreshed daily, snapshot 2026-07-22.