OpenVLM MMBench V1.1 EN - Future Prediction — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 284 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 (2025-08-07) | 89.3 |
| 2 | GPT-4o ChatGPT | 88 |
| 3 | Qwen 2 VL 72B | 86.7 |
| 4 | InternVL2.5-78B | 86.7 |
| 5 | GPT-4.1 (2025-04-14) | 86.7 |
| 6 | InternVL3-78B | 85.3 |
| 7 | InternVL3-38B | 85.3 |
| 8 | Ovis2-8B | 82.7 |
| 9 | Grok 2 (1212) | 82.7 |
| 10 | GPT-4.1 Mini | 81.3 |
| 11 | InternVL3-14B | 81.3 |
| 12 | Gemini 2.5 Pro | 80 |
| 13 | GPT-5 Mini (2025-08-07) | 80 |
| 14 | Gemma 3 12B | 78.7 |
| 15 | Llama 3.2 90B Vision Instruct | 78.7 |
Interactive version: theaggregate.ai/benchmark?slug=openvlm-mmbench-v1-1-en-future-prediction · How the rankings work · Data refreshed daily, snapshot 2026-07-22.