Skip to main content
Radar

Every change to the models you run, with its source and its date. Releases, price changes, retirements, API changes, and incidents.Every change to the models you run, with its source.

Follow model changes
BenchLM

KMMLU-Pro

We mirror this table; we do not rank on it.

Data verified 31 confirmed releases in the last 30 daysFollow model changes

Korean National Professional Licensure exams evaluating professional-grade knowledge.

Benchmark score on KMMLU-Pro — September 17, 2026

We mirror the published score view for KMMLU-Pro. A.X K2 leads the public snapshot at 80.5%, followed by Solar Pro 4 (79.2%) and Solar Open 2 (78.4%). We do not use these results to rank models overall.

1Open weights

A.X K2

SK Telecom

80.5%
Context 262K
2Proprietary

Solar Pro 4

Upstage

79.2%
Context 512K
3Open weights

Solar Open 2

Upstage

78.4%
Context 1M

4 modelsKorean BenchmarksKorean-language benchmarkRefreshingDisplay onlyUpdated September 17, 2026

Benchmark score table (4 models)

Score
1
A.X K2SK Telecom · Open weight
80.5%
2
Solar Pro 4Upstage · Closed
79.2%
3
Solar Open 2Upstage · Open weight
78.4%
4
K-EXAONE 2.0LG AI Research · Open weight
69.1%

The published KMMLU-Pro snapshot places A.X K2 first at 80.5%. The third row is 2.1 points behind. The broader top-10 range is 11.4 points, so the table still separates the published systems.

4 models have been evaluated on KMMLU-Pro. The benchmark falls in the Korean Benchmarks category. BenchLM tracks this category separately from its weighted global scoring system, so these results are best compared on the dedicated Korean benchmark views. KMMLU-Pro is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About KMMLU-Pro

Tasks

~2,500 questions

Format

Professional licensure exams

Difficulty

Professional

Freshness and provenance

Version

KMMLU-Pro

Refresh cadence

Static

Staleness state

Refreshing

Question availability

Public benchmark set

RefreshingDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

Questions

What does KMMLU-Pro measure?

Korean National Professional Licensure exams evaluating professional-grade knowledge.

Which model scores highest on KMMLU-Pro?

A.X K2 by SK Telecom currently leads with a score of 80.5% on KMMLU-Pro.

How many models are evaluated on KMMLU-Pro?

4 AI models have been evaluated on KMMLU-Pro on BenchLM.

Compare top models on KMMLU-Pro

A.X K2 vs Solar Pro 4Solar Pro 4 vs Solar Open 2Solar Open 2 vs K-EXAONE 2.0
Last updated: September 17, 2026 · BenchLM version KMMLU-Pro

Know when it’s worth switching models

The model to choose, the cheaper alternative, and the release we would wait on.

Read a sample issue

Join 2,000+ readers.

One email each week. Unsubscribe anytime.