Evals for Every Language - Yiddish (yi): leaderboard
Average score across evaluation tasks in Yiddish (yi), from Evals for Every Language.
Metric: Average Score (%). Source: huggingface.co. Saturation forecast: Around January 2027. 68 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Flash Lite | 77.89 | #191 |
| 2 | Gemini 3.1 Pro (Preview) | 76.67 | #58 |
| 3 | Claude Sonnet 4.5 | 76.62 | #142 |
| 4 | Claude Opus 4.7 | 75.6 | #49 |
| 5 | Claude Sonnet 4 | 75.06 | #199 |
| 6 | GPT-5 | 74.39 | #98 |
| 7 | Claude Sonnet 4.6 | 74.32 | #90 |
| 8 | GPT-4o | 73.78 | #343 |
| 9 | GLM 4.5 Air | 73.49 | #392 |
| 10 | GPT-5.1 | 73.23 | #135 |
| 11 | GPT-5.3 | 73.21 | #103 |
| 12 | GPT-5.2 | 72.61 | #110 |
| 13 | Claude Opus 4.8 | 72.43 | #37 |
| 14 | Nova Pro (v1) | 70.9 | #497 |
| 15 | Claude Haiku 4.5 | 70.46 | #280 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-yi · How It Works · Data refreshed daily, snapshot 2026-10-20.