MEGA-Bench Task - Move Position To Position Hanoi 4 Pole — leaderboard
Metric: Task Score (%). Source: huggingface.co. 44 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 2 VL 72B | 10.7 |
| 2 | GPT-4o Mini | 10.7 |
| 3 | Gemini 2.5 Pro | 7.1 |
| 4 | InternVL3-14B | 7.1 |
| 5 | Qwen 2 VL 7B | 5 |
| 6 | InternVL2.5-2B | 5 |
| 7 | Gemma 3 27B (IT) | 3.6 |
| 8 | Gemma 3 12B (IT) | 3.6 |
| 9 | Gemma 3 4B (IT) | 3.6 |
| 10 | InternVL3-8B | 3.6 |
| 11 | Ovis2-8B | 3.6 |
| 12 | Llama 4 Scout Base | 3.6 |
| 13 | Gemini 2.0 Flash (Preview) | 3.6 |
| 14 | GPT-4o | 1.1 |
| 15 | Claude 3.5 Sonnet (20241022) | 0.4 |
Interactive version: theaggregate.ai/benchmark?slug=mega-bench-task-move-position-to-position-hanoi-4-pole · How the rankings work · Data refreshed daily, snapshot 2026-07-22.