Official benchmarks map / Vaani-Benchmark-V1.0
gnani/gnani is ranked first on the Vaani-Benchmark-V1.0 leaderboard with 13, -0.8% ahead of fonada/kapture-v3. Read live from the Hugging Face API on November 6, 2026.
| # | Model | Organization | Score |
|---|---|---|---|
| 1 | gnani/gnani | gnani | 13 |
| 2 | fonada/kapture-v3 | fonada | 13.1 |
| 3 | bharatgenai/Shrutam-2 | bharatgenai | 17.4 |
| 4 | bharatgenai/Shrutam-HindiASR-1.0 | bharatgenai | 18.1 |
| 5 | SPRINGLab/data2vec_aqc | SPRINGLab | 20.1 |
| 6 | Qwen/Qwen3-ASR-0.6B-hf | Qwen | 20.6 |
| 7 | mistralai/Voxtral-Mini-3B-2507 | mistralai | 21.3 |
| 8 | shunyalabs/pingala-v1-universal | shunyalabs | 22.1 |
| 9 | google/gemma-4-12B | 24.6 | |
| 10 | facebook/omniASR-LLM-1B | 25.6 |
Vaani-Benchmark-V1.0 is a dataset that Hugging Face marks as an official benchmark. Its leaderboard is built automatically from the .eval_results files that model repositories publish, so entries are mostly self-reported by model authors and evaluation settings differ between submissions. A verified tag appears only where Hugging Face marks an entry as verified.
Original board: huggingface.co/datasets/ARTPARK-IISc/Vaani-Benchmark-V1.0
Part of the Hugging Face official benchmarks map by QuantID. Unofficial. Not affiliated with or endorsed by Hugging Face.