Evals for Every Language - Afrikaans (af): leaderboard
Average score across evaluation tasks in Afrikaans (af), 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 Pro (Preview) | 82.86 | #58 |
| 2 | Claude Sonnet 4 | 82.83 | #199 |
| 3 | Claude Opus 4.8 | 81.95 | #37 |
| 4 | GPT-5.1 | 81.46 | #135 |
| 5 | Claude Sonnet 4.6 | 81.45 | #90 |
| 6 | GPT-5.5 | 81.13 | #31 |
| 7 | Claude Sonnet 4.5 | 80.98 | #142 |
| 8 | Claude Opus 4.7 | 80.85 | #49 |
| 9 | Grok 4.20 | 80.55 | #175 |
| 10 | GPT-5 | 80.28 | #98 |
| 11 | GPT-5.3 | 80.11 | #103 |
| 12 | GPT-5.2 | 80.07 | #110 |
| 13 | Mistral Medium 3.1 | 79.95 | #408 |
| 14 | DeepSeek V3.2 Exp | 79.74 | #234 |
| 15 | GPT-4o | 79.37 | #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-af · How It Works · Data refreshed daily, snapshot 2026-10-20.