Benchmark Almanac

KoMT-Bench

EXAONE 3.0 7.8B Inst. 8.92 tops its leaderboard
Not in model cards

Models follow multi-turn instructions in Korean on a translated and culturally adapted version of MT-Bench, reviewed by expert linguists.

In-house set released with EXAONE models.

Made by
LG AI Research
Released
August 2024
Kind
Chat and instructions in many languages
Level
Everyday
Scored
Graded by a model
Answers
Open-ended
Tasks
All public
6
Entries on its own leaderboard, 0 models we track

EXAONE 3.0 7.8B Inst. tops the leaderboard with 8.92

Best score per entry from the benchmark's own leaderboard, read on November 12th, 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. 8.92 EXAONE 3.0 7.8B Inst.
  2. 7.92 Gemma 2 9B Inst.
  3. 7.69 QWEN 2 7B Inst.
  4. 6.06 Llama 3.1 8B Inst.
  5. 5.20 Mistral 7B Inst.
  6. 4.87 Phi 3 7B Inst.
  1. 1 EXAONE 3.0 7.8B Inst. 8.92
  2. 2 Gemma 2 9B Inst. 7.92
  3. 3 QWEN 2 7B Inst. 7.69
  4. 4 Llama 3.1 8B Inst. 6.06
  5. 5 Mistral 7B Inst. 5.20
  6. 6 Phi 3 7B Inst. 4.87

Source: Official KoMT-Bench leaderboard

#EntryScoreSettingDateSource
1 EXAONE 3.0 7.8B Inst. 8.92 Official leaderboard
2 Gemma 2 9B Inst. 7.92 Official leaderboard
3 QWEN 2 7B Inst. 7.69 Official leaderboard
4 Llama 3.1 8B Inst. 6.06 Official leaderboard
5 Mistral 7B Inst. 5.20 Official leaderboard
6 Phi 3 7B Inst. 4.87 Official leaderboard

No lab model card reports it yet

We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark.

More in Multilingual

All 120 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. Nemotron 3 Ultra 550B-A55B Base 90.1%
  • 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%