Benchmark Almanac

HAE-RAE Bench 1.0

HyperClova LK-D2 70.8% tops its leaderboard
Not in model cards
Version 1.0

Models answer Korean questions about vocabulary, history, general knowledge, and reading comprehension. The original evaluation has six tasks.

The authors direct readers to the version 1.0 dataset to reproduce the paper. Version 1.1 replaces its reading comprehension material.

Made by
Guijin Son and colleagues
Released
May 2023
Kind
Knowledge in many languages
Level
School
Scored
Checked automatically
Answers
Multiple choice
Tasks
All public
Measures
Capability
Language
Korean
In and out
Text → Text
Interaction
Single turn
Run by
Anyone
10
Entries on its own leaderboard, 0 models we track

HyperClova LK-D2 tops the leaderboard with 70.8%

Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders.

  1. 1 HyperClova LK-D2 3-shot 70.8%
  2. 2 Polyglot-Ko 12.8B Log-likelihood 59.6%
  3. 3 Polyglot-Ko 5.8B Log-likelihood 59.5%
  4. 4 Polyglot-Ko 3.8B Log-likelihood 54.9%
  5. 5 Polyglot-Ko 1.3B Log-likelihood 50.8%
  6. 6 Text-Davinci-003 3-shot 49.2%
  7. 7 UMT5-XXL Log-likelihood 34.4%
  8. 8 UMT5-XL Log-likelihood 31.2%
  9. 9 UMT5-Base Log-likelihood 26.2%
  10. 10 UMT5-Small Log-likelihood 25.7%

Source: Official HAE-RAE Bench 1.0 leaderboard

#EntryScoreSettingDateSource
1 HyperClova LK-D2 70.8% 3-shot Official leaderboard
2 Polyglot-Ko 12.8B 59.6% Log-likelihood Official leaderboard
3 Polyglot-Ko 5.8B 59.5% Log-likelihood Official leaderboard
4 Polyglot-Ko 3.8B 54.9% Log-likelihood Official leaderboard
5 Polyglot-Ko 1.3B 50.8% Log-likelihood Official leaderboard
6 Text-Davinci-003 49.2% 3-shot Official leaderboard
7 UMT5-XXL 34.4% Log-likelihood Official leaderboard
8 UMT5-XL 31.2% Log-likelihood Official leaderboard
9 UMT5-Base 26.2% Log-likelihood Official leaderboard
10 UMT5-Small 25.7% Log-likelihood Official leaderboard

No lab model card reports it yet

We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.

Versions

More in Multilingual

All 545 in Multilingual
  • MMMLU In use MMLU professionally translated into 14 languages. Multiple-choice accuracy. Claude Mythos Preview 92.7%
  • WMT24++ In use English-to-55-language translation of WMT24 test data. Scored with automatic metrics such as MetricX or xCOMET. K-EXAONE 90.5%
  • MMLU-ProX In use MMLU-Pro translated into up to 29 languages with expert review. Multiple-choice accuracy per language. Qwen3.7-Max 87%
  • CLIcK In use Models answer 1,995 multiple-choice questions on Korean language and culture. Questions come from official Korean exams and textbooks in eleven categories. Solar Open 2 90.7%
  • Global MMLU Lite 3.0 In use Models answer 400 human-translated MMLU questions per language in 23 languages. Version 3.0 adds Czech, Hungarian, Oriya, Slovak and Tajik and updates Italian. Accuracy. Claude Opus 5 95.7%
  • MMMB In use Models answer multiple-choice questions about images in six languages across 15 categories. The set has about 12,000 questions. LFM2.5-VL-3B 83%

Data audit

All 8 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
  • Pass Independent runs Scores from the official leaderboard (10 entries).
  • Pass Models scored 10 entries on its leaderboard, none a model we track.
  • Note Newest score No scores yet.
  • Note Frontier models No models scored yet.
  • Note Headroom No scores yet.
Leaderboard import 3 pass
  • Pass Importer We read the board on github.com: 10 entries at the last read, none a model we track.
  • Pass Last read November 20th, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check