Benchmark
Open Asr Leaderboard
Scores are percentages. Lower is better.
- Models measured
- 8
- Scores recorded
- 8
- Sources
- 1
- IQ weight
- 0.85
Score distribution
- 6.7%
- Mean
- 7.1%
- Median
- 0.905%
- Std dev
- 5.8%
- 10th percentile
- 7.8%
- 90th percentile
- 5.4%
- Min
This benchmark has a weight of 0.85 for speech models, measured over 7 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Cohere Transcribe 03 2026· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 5.4% |
| 2 | Qwen3 ASR 1.7B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 5.8% |
| 3 | Phi 4 Multimodal Instruct· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 6% |
| 4 | Qwen3 ASR 0.6B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 6.4% |
| 5 | Voxtral Mini 3B 2507· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 7.1% |
| 6 | Whisper Large V3· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 7.4% |
| 7 | Whisper Large v2· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 7.8% |
| 8 | Whisper Large· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 7.9% |
Data credits: Hugging Face official benchmark leaderboards; licence varies by benchmark