Evals for Every Language - Lithuanian (lt): leaderboard
Average score across evaluation tasks in Lithuanian (lt), from Evals for Every Language.
Metric: Average Score (%). Source: huggingface.co. Saturation forecast: Around January 2027. 67 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 79.02 | #58 |
| 2 | Claude Sonnet 4.5 | 78.33 | #142 |
| 3 | Claude Opus 4.8 | 76.45 | #37 |
| 4 | GPT-5.2 | 76.43 | #110 |
| 5 | GPT-5.3 | 75.4 | #103 |
| 6 | Claude Opus 4.7 | 74.64 | #49 |
| 7 | Claude Sonnet 4 | 74.55 | #199 |
| 8 | Claude Sonnet 4.6 | 74.15 | #90 |
| 9 | Gemini 3.1 Flash Lite | 74.05 | #191 |
| 10 | GPT-5.5 | 73.87 | #31 |
| 11 | GPT-5 | 73.3 | #98 |
| 12 | Grok 4.20 | 73.27 | #175 |
| 13 | GPT-5 Nano | 73.17 | #425 |
| 14 | GLM 4.5 Air | 72.98 | #392 |
| 15 | GPT-4o | 72.76 | #343 |
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-lt · How It Works · Data refreshed daily, snapshot 2026-10-20.