MEGA-Bench Task - Healthcare Info Judgement: leaderboard
Metric: Task Score (%). Source: huggingface.co. 44 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Pixtral-12B | 100 |
| 2 | GPT-4o | 92.9 |
| 3 | GPT-4o Mini | 92.9 |
| 4 | Gemini 1.5 Pro (002) | 92.9 |
| 5 | Gemini 1.5 Flash (002) | 92.9 |
| 6 | InternVL2.5-78B | 92.9 |
| 7 | Gemma 3 12B (IT) | 85.7 |
| 8 | Gemma 3 4B (IT) | 85.7 |
| 9 | InternVL2.5-2B | 85.7 |
| 10 | Qwen 2 VL 72B | 78.6 |
| 11 | Qwen 2 VL 7B | 78.6 |
| 12 | InternVL3-38B | 78.6 |
| 13 | Gemini 2.5 Pro (Preview 03-25) | 78.6 |
| 14 | Gemma 3 27B (IT) | 71.4 |
| 15 | InternVL3-78B | 71.4 |
Interactive version: theaggregate.ai/benchmark?slug=mega-bench-task-healthcare-info-judgement · How It Works · Data refreshed daily, snapshot 2026-09-05.