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

#ModelScore
1Gemini 3 Flash (Preview)65.43
2GPT-5.258
3Qwen 3 VL 8B Instruct53.29
4Gemma 3 27B (IT)53.14
5Gemma 3 12B (IT)48.57
6Qwen 3 30B A3B Instruct46.57
7Qwen 2.5 7B Instruct45.43
8Qwen 3 VL 30B A3B Instruct39.71

Interactive version: theaggregate.ai/benchmark?slug=tabverse-qa-markdown-text · How It Works · Data refreshed daily, snapshot 2026-09-29.