Evals for Every Language - Persian (fa): leaderboard
Average score across evaluation tasks in Persian (fa), 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) | 77.72 | #58 |
| 2 | Gemini 2.5 Pro | 76.76 | #152 |
| 3 | GPT-5 | 76.52 | #98 |
| 4 | Grok 4.20 | 76.25 | #175 |
| 5 | Claude Sonnet 4 | 76 | #199 |
| 6 | Claude Sonnet 4.5 | 75.94 | #142 |
| 7 | Gemini 3.1 Flash Lite | 75.94 | #191 |
| 8 | Claude Opus 4.7 | 75.91 | #49 |
| 9 | Claude Opus 4.8 | 75.85 | #37 |
| 10 | Claude Sonnet 4.6 | 75.45 | #90 |
| 11 | GPT-5.1 | 74.92 | #135 |
| 12 | Claude Haiku 4.5 | 74.18 | #280 |
| 13 | GPT-4o | 73.72 | #343 |
| 14 | Command A | 73.12 | #508 |
| 15 | DeepSeek V3.2 Exp | 73.08 | #234 |
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-fa · How It Works · Data refreshed daily, snapshot 2026-10-20.