Skip to content
The Aggregate

Unified LLM rankings, daily

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

KOFFVQA - Korean OCR: leaderboard

Metric: Score (%). Source: huggingface.co. 82 models tracked.

Top models

#ModelScore
1GPT-4o Mini (2024-07-18)100
2GPT-4.195
3Gemini 2.5 Pro (Preview 03-25)95
4O4 Mini (2025-04-16)95
5O3 (2025-04-16)95
6O1 (2024-12-17)95
7Gemini 2.5 Pro (Preview 05-06)95
8GPT-4.5 (Preview)95
9Gemini 2.0 Flash (001)93.5
10GPT-4o (2024-11-20)91.5
11GPT-4.1 Mini90
12Llama 4 Scout Instruct88.5
13Gemini 2.0 Flash Lite (001)88
14Gemma 3 27B (IT)85
15Gemini 2.5 Flash (Preview 04-17)85

Interactive version: theaggregate.ai/benchmark?slug=koffvqa-korean-ocr · How It Works · Data refreshed daily, snapshot 2026-09-05.

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

Your Aggregate

Sign in to keep your work

Save custom rankings and get 50 free task analyses each day.

Continue with Google Continue with GitHub

No password to remember. Your public profile identifies saved work.

Your Aggregate

Account

  • Saved custom aggregate views
  • 50 free task analyses per day
Sign out