MEGA-Bench Task - Table Understanding FeTaQA — leaderboard
Metric: Task Score (%). Source: huggingface.co. 44 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude 3.5 Sonnet (20241022) | 77.9 |
| 2 | Claude 3.5 Sonnet (20240620) | 70.7 |
| 3 | GPT-4o | 67.9 |
| 4 | Ovis2-8B | 65 |
| 5 | Gemini 2.5 Pro | 63.6 |
| 6 | Qwen 2 VL 72B | 62.9 |
| 7 | InternVL2.5-78B | 61.4 |
| 8 | Qwen 2 VL 7B | 60.7 |
| 9 | InternVL3-38B | 60.7 |
| 10 | GPT-4o Mini | 60 |
| 11 | Gemini 2.0 Flash (Preview) | 59.3 |
| 12 | Gemma 3 27B (IT) | 58.6 |
| 13 | InternVL3-8B | 58.6 |
| 14 | Gemma 3 4B (IT) | 53.6 |
| 15 | Gemini 1.5 Pro (002) | 52.9 |
Interactive version: theaggregate.ai/benchmark?slug=mega-bench-task-table-understanding-fetaqa · How the rankings work · Data refreshed daily, snapshot 2026-07-22.