Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Text Quality Evaluation on OpenAudioBench English subsets (test)

7.43AlpacaEval

Baseline-AR

3.34284.40395.4656.5261Feb 9, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
7.438.276156427.07
2026.02
7.438.276156427.07
2026.02
7.438.276156427.07
2026.02
7.438.276156427.07
2026.02
7.438.276156427.07
2026.02
7.438.276156427.07
2026.02
7.438.276156427.07
2026.02
7.357.74905806.44
7.127.956246486.95
2026.02
6.937.434275235.96
2026.02
6.498.16157106.96
2026.02
6.137.726437166.86
6.017.95896886.67
5.867.744955566.03
2026.02
3.52.9439841.92