MEGA-Bench Task - Visual Prediction Rater Surface Normal Estimation: leaderboard
Metric: Task Score (%). Source: huggingface.co. 44 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro (Preview 03-25) | 90.5 |
| 2 | Gemini 1.5 Pro (002) | 81 |
| 3 | InternVL3-38B | 73.8 |
| 4 | InternVL3-78B | 66.7 |
| 5 | Claude 3.5 Sonnet (20241022) | 66.7 |
| 6 | GPT-4o | 57.1 |
| 7 | Claude 3.5 Sonnet (20240620) | 57.1 |
| 8 | InternVL2.5-78B | 54.8 |
| 9 | Gemma 3 27B (IT) | 42.9 |
| 10 | Gemini 1.5 Flash (002) | 33.3 |
| 11 | Aquila-VL-2B | 26.2 |
| 12 | Qwen 2 VL 72B | 16.7 |
| 13 | Pixtral-12B | 16.7 |
| 14 | Llama 4 Scout Base | 15.5 |
| 15 | Gemma 3 4B (IT) | 11.9 |
Interactive version: theaggregate.ai/benchmark?slug=mega-bench-task-visual-prediction-rater-surface-normal-estimation · How It Works · Data refreshed daily, snapshot 2026-09-05.