MEGA-Bench Task - Stock Info Parsing — leaderboard
Metric: Task Score (%). Source: huggingface.co. 44 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o | 97.5 |
| 2 | InternVL3-78B | 97.5 |
| 3 | Qwen 2 VL 72B | 97.5 |
| 4 | Qwen 2 VL 7B | 97.5 |
| 5 | Claude 3.5 Sonnet (20241022) | 97.5 |
| 6 | Claude 3.5 Sonnet (20240620) | 97.5 |
| 7 | Ovis2-8B | 97.1 |
| 8 | GPT-4o Mini | 97.1 |
| 9 | Gemini 2.5 Pro | 96.6 |
| 10 | Gemini 2.0 Flash (Preview) | 96.6 |
| 11 | InternVL3-8B | 96.2 |
| 12 | InternVL2.5-78B | 96.2 |
| 13 | Gemma 3 27B (IT) | 95.4 |
| 14 | InternVL3-14B | 95 |
| 15 | Gemma 3 12B (IT) | 94.5 |
Interactive version: theaggregate.ai/benchmark?slug=mega-bench-task-stock-info-parsing · How the rankings work · Data refreshed daily, snapshot 2026-07-22.