TabVerse - QA (Markdown Image): leaderboard

Metric: Exact-match accuracy (%) answering table questions from a rendered Markdown-table image; higher is better. Source: arxiv.org. Saturation forecast: Around March 2027. 13 models tracked.

Top models

#ModelScore
1Gemini 3 Flash (Preview)65.43
2GPT-5.256.14
3Qwen 3 VL 8B Instruct49.71
4Gemma 3 27B (IT)45.43
5Qwen 3 VL 30B A3B Instruct41.43
6Gemma 3 12B (IT)38.57

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