MEGA-Bench Task - Visual Prediction Rater Novel View Synthesis — leaderboard
Metric: Task Score (%). Source: huggingface.co. 44 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro | 42.9 |
| 2 | Gemini 2.0 Flash (Preview) | 28.6 |
| 3 | Aquila-VL-2B | 21.4 |
| 4 | Qwen 2 VL 2B | 14.3 |
| 5 | Gemini 1.5 Pro (002) | 14.3 |
| 6 | Llama 4 Scout Base | 14.3 |
| 7 | GPT-4o | 7.1 |
| 8 | Gemma 3 4B (IT) | 7.1 |
| 9 | Qwen 2 VL 72B | 7.1 |
| 10 | Qwen 2 VL 7B | 7.1 |
| 11 | Claude 3.5 Sonnet (20241022) | 7.1 |
| 12 | MiniCPM-V-2.6 | 7.1 |
| 13 | Gemini 1.5 Flash (002) | 7.1 |
| 14 | Gemma 3 27B (IT) | 0 |
| 15 | Gemma 3 12B (IT) | 0 |
Interactive version: theaggregate.ai/benchmark?slug=mega-bench-task-visual-prediction-rater-novel-view-synthesis · How the rankings work · Data refreshed daily, snapshot 2026-07-22.