KOFFVQA - Table Understanding: leaderboard
Metric: Score (%). Source: huggingface.co. 82 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro (Preview 03-25) | 96.67 |
| 2 | Gemini 2.0 Flash (001) | 96.67 |
| 3 | Gemini 2.5 Pro (Preview 05-06) | 96.67 |
| 4 | Gemini 2.5 Flash (Preview 05-20) | 96.67 |
| 5 | Gemini 2.5 Flash (Preview 04-17) | 95.67 |
| 6 | O4 Mini (2025-04-16) | 95.33 |
| 7 | O3 (2025-04-16) | 94 |
| 8 | GPT-4.5 (Preview) | 93.33 |
| 9 | Gemini 2.0 Flash Lite (001) | 90 |
| 10 | GPT-4.1 | 88.67 |
| 11 | O1 (2024-12-17) | 86.67 |
| 12 | Llama 4 Scout Instruct | 85.33 |
| 13 | GPT-4.1 Mini | 85 |
| 14 | Qwen 2 VL 72B Instruct | 84.33 |
| 15 | Gemini 1.5 Flash (002) | 83.33 |
Interactive version: theaggregate.ai/benchmark?slug=koffvqa-table-understanding · How It Works · Data refreshed daily, snapshot 2026-09-05.