Ko-Arena-Hard v2 (Upstage)
Models answer hard user prompts in Korean, judged against a baseline in the style of Arena-Hard v2. Upstage built it in house.
Upstage marks it as in-house on the Solar Open 100B card and reports it again for the March 2026 Solar Pro 3 update. Its Korean prompt source is not published.
- Made by
- Upstage
- Released
- December 2025
- Kind
- Chat and instructions in many languages
- Level
- Everyday
- Scored
- Graded by a model
- Answers
- Open-ended
- Tasks
- Kept private
- Last in a launch post
- March 2026, dropped before it saturated
- Last model added
- March 2026
- Scores refreshed
- November 12th, 2026
Solar Open 100B leads with 79.9%
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
Solar Pro 3 (March 2026 update) leads with 78.2% across all independent runs
Best score per model across the official leaderboard, Epoch AI’s own runs and any board Epoch AI copied. Each bar and row names its source.
- 1
Solar Open 100B 79.9% - 2 Solar Pro 3 (March 2026 update) 78.2%
Source: Labs’ model cards
Source: Official Ko-Arena-Hard v2 (Upstage) leaderboard
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Solar Open 100B | 79.9% | Jan 2026 | Lab model card | |
| 2 | Solar Pro 3 (March 2026 update) | 78.2% | Mar 2026 | Lab model card |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Solar Pro 3 (March 2026 update) | 78.2% | Mar 2026 | Official leaderboard |
The benchmark's own leaderboard has 2 entries, 1 of them models we track. Switch the scores above to rank them together.
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Sources: Official Ko-Arena-Hard v2 (Upstage) leaderboard and labs’ model cards
Labs headline it less often now, last in March 2026
Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| Mar 24, 2026 | Solar Pro 3 (March 2026 update) | 78.2 | Ko-Arena-hard-v2 |
One system card reports it
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| Jan 11, 2026 | Solar Open 100B technical report | 79.9 | Ko Arena Hard v2 (in-house) (Table 5) | Capabilities |
One lab claim next to the leaderboard
Each score a lab reported for its own model, beside the same model's best score on the leaderboard. Gaps mostly come from different harnesses, effort levels and task subsets. 1 of them match, which usually means one side copied the other. Every benchmark.
| Model | Lab says | Board says | Gap |
|---|---|---|---|
| Solar Pro 3 (March 2026 update) | 78.2% Ko-Arena-hard-v2 | 78.2% Leaderboard | Same |
More 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%