OpenVLM MMT-Bench - Profession Recognition — leaderboard
Metric: Score (%). Source: huggingface.co. 207 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | InternVL2-8B | 95 |
| 2 | GPT-4.1 Nano | 95 |
| 3 | Pixtral-12B | 95 |
| 4 | Gemma 3 27B | 95 |
| 5 | Claude 3.5 Sonnet | 95 |
| 6 | Gemma 3 12B | 95 |
| 7 | Gemma 3 4B | 95 |
| 8 | Claude 3 Haiku | 95 |
| 9 | GPT-4.1 Mini | 90 |
| 10 | InternVL3-78B | 90 |
| 11 | InternVL3-8B | 90 |
| 12 | Qwen 2 VL 72B | 90 |
| 13 | Qwen 2 VL 7B | 90 |
| 14 | InternVL3-38B | 90 |
| 15 | Qwen 2 VL 2B | 90 |
Interactive version: theaggregate.ai/benchmark?slug=openvlm-mmt-bench-profession-recognition · How the rankings work · Data refreshed daily, snapshot 2026-07-22.