TabVerse - QA (HTML Text): leaderboard

Metric: Exact-match accuracy (%) answering table questions from HTML table text; higher is better. Source: arxiv.org. Saturation forecast: Around March 2028. 17 models tracked.

Top models

#ModelScore
1Gemini 3 Flash (Preview)65.71
2GPT-5.257.43
3Gemma 3 27B (IT)53.43
4Qwen 3 VL 8B Instruct53.43
5Qwen 3 30B A3B Instruct51.14
6Gemma 3 12B (IT)50.29
7Qwen 3 VL 30B A3B Instruct45.29
8Qwen 2.5 7B Instruct44.57

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