MEGA-Bench - Output Format: Multiple Choice: leaderboard
Metric: Average Score (%). Source: huggingface.co. 44 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro (Preview 03-25) | 70.8 |
| 2 | Claude 3.5 Sonnet (20241022) | 57.8 |
| 3 | Gemini 1.5 Pro (002) | 55.4 |
| 4 | Claude 3.5 Sonnet (20240620) | 54.6 |
| 5 | GPT-4o | 54.5 |
| 6 | Qwen 2 VL 72B | 50.6 |
| 7 | Gemini 1.5 Flash (002) | 47.2 |
| 8 | InternVL2.5-78B | 47.2 |
| 9 | InternVL3-38B | 45.7 |
| 10 | Gemma 3 27B (IT) | 45 |
| 11 | InternVL3-78B | 44.6 |
| 12 | GPT-4o Mini | 39.9 |
| 13 | Qwen 2 VL 7B | 38.1 |
| 14 | Gemma 3 12B (IT) | 37.7 |
| 15 | InternVL3-8B | 33.9 |
Interactive version: theaggregate.ai/benchmark?slug=mega-bench-output-format-multiple-choice · How It Works · Data refreshed daily, snapshot 2026-09-05.