Evals for Every Language - Language ko: leaderboard
Metric: Average Score (%). Source: huggingface.co. 71 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 69.88 |
| 2 | Claude Sonnet 4 | 68.75 |
| 3 | Claude Sonnet 4.5 | 68.52 |
| 4 | Claude Sonnet 4.6 | 66.93 |
| 5 | GPT-5.1 | 66.88 |
| 6 | Claude Opus 4.8 | 66.65 |
| 7 | Grok 4.20 | 65.73 |
| 8 | GPT-5 | 65.21 |
| 9 | GPT-5.5 | 65.16 |
| 10 | GPT-5.3 | 64.84 |
| 11 | Claude Opus 4.7 | 64.63 |
| 12 | Gemini 2.5 Pro | 64.34 |
| 13 | GPT-5.2 | 63.9 |
| 14 | GPT-4o | 63.35 |
| 15 | GPT-5.4 | 63.29 |
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-ko · How It Works · Data refreshed daily, snapshot 2026-09-05.