MEGA-Bench Task - Planning Screenshot Barman: leaderboard
Metric: Task Score (%). Source: huggingface.co. 44 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro (Preview 03-25) | 40 |
| 2 | Claude 3.5 Sonnet (20241022) | 6.7 |
| 3 | InternVL2.5-78B | 6.7 |
| 4 | Gemma 3 27B (IT) | 0 |
| 5 | GPT-4o | 0 |
| 6 | Gemma 3 12B (IT) | 0 |
| 7 | Gemma 3 4B (IT) | 0 |
| 8 | InternVL3-78B | 0 |
| 9 | InternVL3-8B | 0 |
| 10 | InternVL2-8B | 0 |
| 11 | Qwen 2 VL 72B | 0 |
| 12 | Qwen 2 VL 7B | 0 |
| 13 | InternVL3-38B | 0 |
| 14 | Qwen 2 VL 2B | 0 |
| 15 | Aquila-VL-2B | 0 |
Interactive version: theaggregate.ai/benchmark?slug=mega-bench-task-planning-screenshot-barman · How It Works · Data refreshed daily, snapshot 2026-09-05.