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...

MMLongBench-Doc - Accuracy — leaderboard

Metric: Accuracy (%). Source: huggingface.co. 19 models tracked.

Top models

#ModelScore
1Claude Opus 4.561.9
2Qwen 3.5 397B A17B61.5
3Gemini 3 Pro60.5
4Qwen 3 VL 235B A22B Instruct57
5Qwen 3 VL 235B A22B (Thinking)56.2
6GLM-4.6V54.9
7GLM-4.5V44.7

Interactive version: theaggregate.ai/benchmark?slug=mmlongbench-doc-accuracy · 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.