Skip to content

Benchmark

FLEURS · S2TT · Chinese→Cantonese · BLEU

Higher scores are better.

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

Score distribution

36.3
Mean
36.7
Median
0.4
Std dev
35.9
10th percentile
36.7
90th percentile
35.9
Min
35.936.7
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Qwen3.5 Omni PlusTechnical report v2 · Table 14 · Chinese→Cantonese· Reported by Qwen Team· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.36.7
2Qwen3.5 Omni FlashTechnical report v2 · Table 14 · Chinese→Cantonese· Reported by Qwen Team· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.35.9

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.