Evals for Every Language - Sanskrit (sa): leaderboard
Average score across evaluation tasks in Sanskrit (sa), from Evals for Every Language.
Metric: Average Score (%). Source: huggingface.co. Saturation forecast: Around January 2027. 65 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 71.75 | #58 |
| 2 | GPT-5 | 71.71 | #98 |
| 3 | GPT-5.2 | 71.04 | #110 |
| 4 | Claude Sonnet 4 | 70.07 | #199 |
| 5 | Claude Sonnet 4.6 | 69.9 | #90 |
| 6 | GPT-5.3 | 69 | #103 |
| 7 | GPT-5.1 | 68.93 | #135 |
| 8 | Claude Opus 4.7 | 68.78 | #49 |
| 9 | Claude Sonnet 4.5 | 68.69 | #142 |
| 10 | GPT-4o | 67.55 | #343 |
| 11 | DeepSeek V3.2 Exp | 67.02 | #234 |
| 12 | Claude Opus 4.8 | 66.81 | #37 |
| 13 | Grok 4.20 | 66.46 | #175 |
| 14 | Gemini 3.1 Flash Lite | 66.41 | #191 |
| 15 | Qwen 3.6 Flash | 66.39 | #214 |
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-sa · How It Works · Data refreshed daily, snapshot 2026-10-20.