TabVerse - QA (HTML Image): leaderboard

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

Top models

#ModelScore
1Gemini 3 Flash (Preview)65.43
2GPT-5.254.57
3Qwen 3 VL 8B Instruct50.29
4Gemma 3 27B (IT)46.14
5Qwen 3 VL 30B A3B Instruct41.14
6Gemma 3 12B (IT)38.86

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