TabVerse - QA (Markdown Text): leaderboard
Metric: Exact-match accuracy (%) answering table questions from Markdown table text; higher is better. Source: arxiv.org. Saturation forecast: Around January 2028. 17 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Flash (Preview) | 65.43 |
| 2 | GPT-5.2 | 58 |
| 3 | Qwen 3 VL 8B Instruct | 53.29 |
| 4 | Gemma 3 27B (IT) | 53.14 |
| 5 | Gemma 3 12B (IT) | 48.57 |
| 6 | Qwen 3 30B A3B Instruct | 46.57 |
| 7 | Qwen 2.5 7B Instruct | 45.43 |
| 8 | Qwen 3 VL 30B A3B Instruct | 39.71 |
Interactive version: theaggregate.ai/benchmark?slug=tabverse-qa-markdown-text · How It Works · Data refreshed daily, snapshot 2026-09-29.