Skip to content

The Aggregate

Unified LLM rankings, daily

Models What's New Trends Benchmarks Skill Maps
How It Works Guesswork Metrics
The Aggregate
Loading data...

LLM Stats (TextVQA) — leaderboard

Metric: Score (%). Source: llm-stats.com. 15 models tracked.

Top models

#ModelScore
1Qwen 2 VL 72B Instruct85.5
2Qwen 2.5 VL 7B Instruct84.9
3Qwen2.5-Omni-7B84.4
4Nova Pro81.5
5Nova Lite80.2
6Phi-4 Multimodal Instruct75.6
7Llama 3.2 90B Instruct73.5
8Gemma 3 12B67.7
9Gemma 3 27B65.1
10Gemma 3 4B57.8

Interactive version: theaggregate.ai/benchmark?slug=llm-stats-textvqa · How the rankings work · Data refreshed daily, snapshot 2026-07-22.

Built by Mikhail Doroshenko — AI researcher, co-author of Humanity’s Last Exam. Independent project; no affiliation with any AI lab.