Evals for Every Language - Esperanto (eo): leaderboard
Average score across evaluation tasks in Esperanto (eo), 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 Flash Lite | 80.62 | #191 |
| 2 | Claude Sonnet 4.5 | 80.01 | #142 |
| 3 | Gemini 3.1 Pro (Preview) | 79.4 | #58 |
| 4 | Claude Opus 4.7 | 79.13 | #49 |
| 5 | GPT-4o | 78.5 | #343 |
| 6 | Claude Opus 4.8 | 78.48 | #37 |
| 7 | GPT-5 | 78.23 | #98 |
| 8 | GPT-5.1 | 78.02 | #135 |
| 9 | GPT-5.2 | 77.39 | #110 |
| 10 | Claude Sonnet 4 | 77.2 | #199 |
| 11 | GPT-5.3 | 77.04 | #103 |
| 12 | Gemma 3 27B (IT) | 76.66 | #523 |
| 13 | Qwen 3.6 Plus | 75.08 | #120 |
| 14 | GPT-5.5 | 75.05 | #31 |
| 15 | Claude Sonnet 4.6 | 74.73 | #90 |
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-eo · How It Works · Data refreshed daily, snapshot 2026-10-20.