Codesota · OCR · Benchmarks · audiobenchHome/OCR/Benchmarks/audiobench
Unknown

audiobench.

OCR benchmark

§ 01 · avg-score

avg-score.

Higher is better

#ModelScoreSource
★
WavLLM
Fetched from CodeSOTA API on 2026-04-20
50.25codesota-api
2
SALMONN
Fetched from CodeSOTA API on 2026-04-20
43.99codesota-api
3
Qwen2-Audio-Instruct
Fetched from CodeSOTA API on 2026-04-20
42.12codesota-api
4
Whisper+LLaMA-3 (cascade)
Fetched from CodeSOTA API on 2026-04-20
40.9codesota-api
5
Qwen-Audio-Chat
Fetched from CodeSOTA API on 2026-04-20
38.59codesota-api
§ Related · Explore

More OCR content.

Verified Model Reviews
Comparisons & Guides
View all OCR benchmarks →← Back to All Benchmarks