Skip to content

Benchmark

Common Voice 15 · Mandarin WER/CER

Scores are percentages. Lower is better.

Models measured
2
Scores recorded
2
Sources
1
IQ weight
No weight published

Score distribution

3.9%
Mean
4.3%
Median
0.395%
Std dev
3.5%
10th percentile
4.3%
90th percentile
3.5%
Min
3.5%4.3%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Qwen3.5 Omni PlusQwen3.5-Omni release · ASR WER/CER · lower is better · Mandarin· Reported by Qwen, Qwen Team· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.3.5%
2Qwen3.5 Omni FlashQwen3.5-Omni release · ASR WER/CER · lower is better · Mandarin· Reported by Qwen, Qwen Team· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.4.3%

Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links.