Skip to content

Benchmark

Voice Clone · In-house · Urdu SIM

Higher scores are better.

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

Score distribution

0.775
Mean
0.775
Median
0
Std dev
0.775
10th percentile
0.775
90th percentile
0.775
Min

Leaderboard

#ModelScore
1Qwen3.5 Omni PlusTechnical report v2 · Table 10 · Urdu · internal FLEURS-derived set · cosine speaker similarity· Reported by Qwen Team· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.0.775

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.