MMTU - Table Understanding: leaderboard
Metric: Accuracy (%). Source: huggingface.co. 26 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 Mini | 93.25 |
| 2 | GPT-5 | 92.95 |
| 3 | O3 | 88.34 |
| 4 | Gemini 2.5 Pro | 84.24 |
| 5 | Gemini 2.5 Flash | 82.04 |
| 6 | Grok 3 Mini | 78.99 |
| 7 | GPT-OSS-120B | 74.73 |
| 8 | GPT-OSS-20B | 68.48 |
| 9 | Qwen 3 235B A22B 2507 (Thinking) | 67.34 |
| 10 | GPT-5 Chat | 59.13 |
| 11 | Qwen 3 235B A22B 2507 Instruct | 57.62 |
| 12 | DeepSeek R1 0528 | 53.81 |
| 13 | GPT-4o (2024-11-20) | 46.97 |
| 14 | Llama 4 Maverick Instruct FP8 | 42.12 |
| 15 | Qwen 3 32B | 26.46 |
Interactive version: theaggregate.ai/benchmark?slug=mmtu-table-understanding · How It Works · Data refreshed daily, snapshot 2026-09-05.