OpenVLM MMT-Bench - LVLM Response Judgement: leaderboard
Metric: Score (%). Source: huggingface.co. 207 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4.1 (2025-04-14) | 70 |
| 2 | InternVL3-78B | 65 |
| 3 | InternVL2-8B | 65 |
| 4 | Qwen 2 VL 72B | 60 |
| 5 | GPT-4.1 Nano | 60 |
| 6 | Gemini 1.5 Pro | 60 |
| 7 | Grok 2 (1212) | 60 |
| 8 | Gemma 3 4B | 60 |
| 9 | Llama 3.2 90B Vision Instruct | 60 |
| 10 | GPT-4.1 Mini | 55 |
| 11 | Aquila-VL-2B | 55 |
| 12 | Pixtral-12B | 55 |
| 13 | Gemini 1.5 Flash | 55 |
| 14 | Gemma 3 12B | 55 |
| 15 | InternVL3-8B | 50 |
Interactive version: theaggregate.ai/benchmark?slug=openvlm-mmt-bench-lvlm-response-judgement · How It Works · Data refreshed daily, snapshot 2026-09-05.