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...

KOFFVQA - Korean Recognition — leaderboard

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

Top models

#ModelScore
1O1 (2024-12-17)100
2GPT-4o (2024-08-06)90
3O3 (2025-04-16)90
4Gemini 2.5 Pro (Preview 05-06)90
5Gemini 2.5 Pro (03-25)90
6Gemini 2.0 Pro (Preview 02-05)90
7Gemini 2.5 Flash (Preview 05-20)90
8GPT-4.185
9GPT-4o (2024-11-20)85
10Gemini 2.5 Flash (Preview 04-17)85
11Claude 3.5 Sonnet (20241022)80
12GPT-4.5 (Preview)80
13Gemini 2.0 Flash (Preview)70
14Gemini 2.0 Flash (001)70
15O4 Mini (2025-04-16)70

Interactive version: theaggregate.ai/benchmark?slug=koffvqa-korean-recognition · 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.