Evals for Every Language - Sindhi (sd): leaderboard
Average score across evaluation tasks in Sindhi (sd), 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 4.7 | 77 | #49 |
| 2 | Gemini 3.1 Flash Lite | 76.81 | #191 |
| 3 | Gemini 3.1 Pro (Preview) | 76.77 | #58 |
| 4 | GPT-5.1 | 76.46 | #135 |
| 5 | Gemini 2.5 Pro | 75.72 | #152 |
| 6 | GPT-5.3 | 75.58 | #103 |
| 7 | Claude Sonnet 4.5 | 74.88 | #142 |
| 8 | Claude Sonnet 4 | 74.21 | #199 |
| 9 | GPT-4o | 74.17 | #343 |
| 10 | Qwen 3.6 Plus | 74.03 | #120 |
| 11 | DeepSeek V3.2 Exp | 73.96 | #234 |
| 12 | Claude Sonnet 4.6 | 73.67 | #90 |
| 13 | GPT-5.2 | 73.31 | #110 |
| 14 | GPT-5.5 | 73.24 | #31 |
| 15 | Claude Opus 4.8 | 73.17 | #37 |
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-sd · How It Works · Data refreshed daily, snapshot 2026-10-20.