OpenVLM MMBench V1.1 EN - Function Reasoning: leaderboard
Metric: Accuracy (%). Source: huggingface.co. 284 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | InternVL2.5-78B | 98.9 |
| 2 | Llama 3.2 90B Vision Instruct | 97.8 |
| 3 | Gemini 1.5 Flash (002) | 96.7 |
| 4 | Grok 2 (1212) | 96.7 |
| 5 | Gemini 1.5 Flash | 96.7 |
| 6 | InternVL3-78B | 95.6 |
| 7 | Gemma 3 12B | 95.6 |
| 8 | GPT-5 Mini (2025-08-07) | 95.6 |
| 9 | Qwen 2 VL 72B | 94.4 |
| 10 | InternVL3-38B | 94.4 |
| 11 | Aquila-VL-2B | 94.4 |
| 12 | Gemini 1.5 Pro (002) | 94.4 |
| 13 | Pixtral-12B | 94.4 |
| 14 | GPT-4.1 (2025-04-14) | 94.4 |
| 15 | GPT-4o ChatGPT | 94.4 |
Interactive version: theaggregate.ai/benchmark?slug=openvlm-mmbench-v1-1-en-function-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-05.