IndicKLAR (Urdu): leaderboard
Metric: Accuracy (%; relaxed prefix match of the answer to 2,619 factual queries in Urdu script, machine-translated, not speaker-verified; direct 3-shot prompting with English examples, greedy decoding). Source: arxiv.org. Saturation forecast: Estimated already saturated. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemma 3 12B (IT) | 68.8 |
| 2 | Qwen 2.5 14B Instruct | 59 |
| 3 | Llama 3.1 8B Instruct | 57 |
| 4 | Qwen 2.5 7B Instruct | 48.5 |
| 5 | Gemma 3 4B (IT) | 48.3 |
| 6 | Llama 3.2 3B Instruct | 40.7 |
| 7 | Llama 3.2 1B Instruct | 26.5 |
| 8 | Qwen 2.5 1.5B Instruct | 25.1 |
| 9 | Gemma 3 1B (IT) | 13.7 |
Interactive version: theaggregate.ai/benchmark?slug=indicklar-urdu · How It Works · Data refreshed daily, snapshot 2026-09-26.