BhashaBench - Ayur - Hindi: leaderboard
From BharatGen's BhashaBench V1 leaderboard, which scores models on English and Hindi questions sourced from Indian government and domain-specific exams. BhashaBench-Ayur tests knowledge of Ayurveda, India's traditional medicine system; this board is accuracy on the Hindi-language questions only (%), higher is better. Flagged runs are skipped.
Metric: Accuracy (%). Source: huggingface.co. Saturation forecast: Around 2029. 31 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3 235B A22B 2507 Instruct | 54.78 | #315 |
| 2 | GPT-4o | 54.73 | #357 |
| 3 | GPT-OSS-120B | 48.05 | #346 |
| 4 | Gemma 2 27B | 42.26 | #803 |
| 5 | Gemma 2 9B | 37.92 | #924 |
| 6 | DeepSeek V3.1 | 37.03 | #275 |
| 7 | Gemma 2 27B (IT) | 33.89 | #652 |
| 8 | GPT-OSS-20B | 33.09 | #523 |
| 9 | Pangea-7B | 31.93 | #1223 |
| 10 | Qwen 2.5 3B | 31.9 | #1177 |
| 11 | Indic-gemma-7B-finetuned-sft-Navarasa-2.0 | 31.83 | #1372 |
| 12 | Llama 3.1 8B Instruct | 31.26 | #1017 |
| 13 | Gemma 2 9B (IT) | 31.18 | #795 |
| 14 | Gemma 2 2B | 30.61 | #1466 |
| 15 | Llama 3.2 3B Instruct | 29.67 | #1327 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=bhashabench-ayur-hindi · How It Works · Data refreshed daily, snapshot 2026-11-05.