Skip to content

Benchmark

Common Voice 15 · Traditional Chinese WER/CER

Scores are percentages. Lower is better.

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

Score distribution

2.5%
Mean
2.7%
Median
0.205%
Std dev
2.3%
10th percentile
2.7%
90th percentile
2.3%
Min
2.3%2.7%
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 · Traditional Chinese· Reported by Qwen, Qwen Team· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.2.3%
2Qwen3.5 Omni FlashQwen3.5-Omni release · ASR WER/CER · lower is better · Traditional Chinese· Reported by Qwen, Qwen Team· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.2.7%

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.