MEGA-Bench Task - Paper Review Rating: leaderboard
The "Paper Review Rating" subtask of MEGA-Bench Task. A single task from MEGA-Bench, a large-scale multimodal evaluation suite that scores vision-language models across 500+ real-world tasks spanning perception, reasoning, OCR, charts, documents, and multi-image understanding.
Metric: Task Score (%). Source: huggingface.co. 44 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.0 Flash (Preview) | 76.4 | #370 |
| 2 | InternVL2.5-2B | 76.4 | #1249 |
| 3 | Gemma 3 12B (IT) | 75.8 | #664 |
| 4 | Gemini 1.5 Flash (002) | 75.6 | #583 |
| 5 | Llama 4 Scout Base | 75.2 | #707 |
| 6 | InternVL2-8B | 72.7 | #817 |
| 7 | Qwen 2 VL 7B | 71.4 | #750 |
| 8 | Aquila-VL-2B | 71.4 | #1238 |
| 9 | Gemini 1.5 Pro (002) | 70.9 | #349 |
| 10 | InternVL3-14B | 70.4 | #505 |
| 11 | Gemma 3 27B (IT) | 70.1 | #523 |
| 12 | Qwen 2 VL 72B | 69.9 | #460 |
| 13 | Qwen 2 VL 2B | 67.9 | #1220 |
| 14 | Claude 3.5 Sonnet (20241022) | 67.6 | #291 |
| 15 | Gemini 2.5 Pro (Preview 03-25) | 67.6 | #123 |
Interactive version: theaggregate.ai/benchmark?slug=mega-bench-task-paper-review-rating · How It Works · Data refreshed daily, snapshot 2026-10-20.