Evals for Every Language - Somali (so): leaderboard
Average score across evaluation tasks in Somali (so), from Evals for Every Language.
Metric: Average Score (%). Source: huggingface.co. Saturation forecast: Around January 2027. 66 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.8 | 75.37 | #37 |
| 2 | Gemini 3.1 Pro (Preview) | 75.33 | #58 |
| 3 | Claude Opus 4.7 | 75.31 | #49 |
| 4 | GPT-4o | 74.28 | #343 |
| 5 | Claude Sonnet 4.5 | 73.47 | #142 |
| 6 | Grok 4.20 | 73.28 | #175 |
| 7 | GPT-5.3 | 73.13 | #103 |
| 8 | GPT-5.2 | 73.02 | #110 |
| 9 | Gemini 3.1 Flash Lite | 72.57 | #191 |
| 10 | Claude Sonnet 4.6 | 72.33 | #90 |
| 11 | GPT-5 | 72.06 | #98 |
| 12 | GPT-5.1 | 71.98 | #135 |
| 13 | Qwen 3.6 Plus | 70.99 | #120 |
| 14 | GPT-4.1 | 70.85 | #248 |
| 15 | GPT-5.5 | 70.65 | #31 |
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-so · How It Works · Data refreshed daily, snapshot 2026-10-20.