OpenVLM MMBench V1.1 CN - Future Prediction: leaderboard
Metric: Accuracy (%). Source: huggingface.co. 284 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 | 88 |
| 2 | InternVL2.5-78B | 88 |
| 3 | GPT-4o ChatGPT | 88 |
| 4 | GPT-4.1 (2025-04-14) | 86.7 |
| 5 | Qwen 2 VL 72B | 85.3 |
| 6 | Claude 3.5 Sonnet (20241022) | 84 |
| 7 | GPT-5 Mini (2025-08-07) | 84 |
| 8 | InternVL3-38B | 82.7 |
| 9 | GPT-5 Nano | 82.7 |
| 10 | Grok 2 (1212) | 82.7 |
| 11 | InternVL3-78B | 81.3 |
| 12 | Gemma 3 27B | 81.3 |
| 13 | GPT-4.1 Mini | 80 |
| 14 | Gemini 1.5 Flash (002) | 80 |
| 15 | GPT-4.5 | 80 |
Interactive version: theaggregate.ai/benchmark?slug=openvlm-mmbench-v1-1-cn-future-prediction · How It Works · Data refreshed daily, snapshot 2026-09-05.