OMLAB Open Agent Multimodal Leaderboard — leaderboard
Open Agent Leaderboard multimodal track where visual agents interpret screen state, choose actions, and complete interactive tasks.
Metric: Score. Source: huggingface.co. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen2.5-VL-72B-Instruct (ZoomEye) | 51.56 |
| 2 | Qwen2.5-VL-7B-Instruct (ZoomEye) | 48.06 |
| 3 | Qwen2.5-VL-72B-Instruct (IO) | 44.47 |
| 4 | InternVL2.5-8B (ZoomEye) | 43.42 |
| 5 | InternVL2.5-8B (IO) | 42.95 |
| 6 | Qwen2.5-VL-7B-Instruct (IO) | 42.86 |
| 7 | Llava-v1.5-7B (ZoomEye) | 31.6 |
| 8 | Llava-v1.5-7B (IO) | 24.79 |
| 9 | seal_vqa & seal_vsm (V*) | 15.14 |
Interactive version: theaggregate.ai/benchmark?slug=omlab-open-agent-multimodal-leaderboard · How the rankings work · Data refreshed daily, snapshot 2026-07-22.