MEGA-Bench Task - Visualization With Code — leaderboard
Metric: Task Score (%). Source: huggingface.co. 44 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro | 77.9 |
| 2 | Gemini 2.0 Flash (Preview) | 67.1 |
| 3 | Claude 3.5 Sonnet (20241022) | 66.4 |
| 4 | Claude 3.5 Sonnet (20240620) | 65 |
| 5 | GPT-4o | 63.6 |
| 6 | Gemini 1.5 Flash (002) | 57.1 |
| 7 | GPT-4o Mini | 51.4 |
| 8 | Gemini 1.5 Pro (002) | 51.4 |
| 9 | Qwen 2 VL 72B | 49.3 |
| 10 | Gemma 3 27B (IT) | 47.9 |
| 11 | InternVL3-78B | 45 |
| 12 | InternVL3-38B | 42.1 |
| 13 | InternVL3-14B | 41.4 |
| 14 | InternVL2.5-78B | 39.3 |
| 15 | Pixtral-12B | 37.1 |
Interactive version: theaggregate.ai/benchmark?slug=mega-bench-task-visualization-with-code · How the rankings work · Data refreshed daily, snapshot 2026-07-22.