Evals for Every Language - Punjabi (pa): leaderboard
Average score across evaluation tasks in Punjabi (pa), 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 | Gemini 3.1 Pro (Preview) | 81.8 | #58 |
| 2 | GPT-5.5 | 80.75 | #31 |
| 3 | GPT-5 | 80.72 | #98 |
| 4 | GPT-5.1 | 80.11 | #135 |
| 5 | Gemini 3.1 Flash Lite | 79.93 | #191 |
| 6 | Claude Opus 4.8 | 79.27 | #37 |
| 7 | Qwen 3.6 Plus | 79.1 | #120 |
| 8 | GPT-5.3 | 78.22 | #103 |
| 9 | Mistral Medium 3.1 | 77.81 | #408 |
| 10 | GPT-5.2 | 77.7 | #110 |
| 11 | Grok 4.20 | 77.67 | #175 |
| 12 | Claude Opus 4.7 | 77.48 | #49 |
| 13 | Claude Sonnet 4.6 | 77.39 | #90 |
| 14 | Claude Sonnet 4 | 76.6 | #199 |
| 15 | Nova Pro (v1) | 76.44 | #497 |
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-pa · How It Works · Data refreshed daily, snapshot 2026-10-20.