MEGA-Bench Task - Graph Shortest Path Planar: leaderboard
Metric: Task Score (%). Source: huggingface.co. 44 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro (Preview 03-25) | 57.1 |
| 2 | InternVL3-78B | 42.9 |
| 3 | InternVL3-38B | 42.9 |
| 4 | GPT-4o Mini | 35.7 |
| 5 | Gemini 1.5 Flash (002) | 35.7 |
| 6 | InternVL2.5-78B | 35.7 |
| 7 | GPT-4o | 28.6 |
| 8 | Gemma 3 12B (IT) | 28.6 |
| 9 | Gemma 3 4B (IT) | 28.6 |
| 10 | Qwen 2 VL 7B | 28.6 |
| 11 | Claude 3.5 Sonnet (20240620) | 28.6 |
| 12 | Gemma 3 27B (IT) | 21.4 |
| 13 | Qwen 2 VL 72B | 21.4 |
| 14 | Claude 3.5 Sonnet (20241022) | 21.4 |
| 15 | Aquila-VL-2B | 21.4 |
Interactive version: theaggregate.ai/benchmark?slug=mega-bench-task-graph-shortest-path-planar · How It Works · Data refreshed daily, snapshot 2026-09-05.