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

Question Answering on VoiceBench

89.23OpenbookQA Score

GPT-4O-AUDIO

51.977261.648671.3280.9914Jul 2, 2026
Updated 23d ago

Evaluation Results

MethodLinks
2026.07
89.2380.25
2026.07
86.5973.38
2026.07
83.5262.17
2026.07
83.5271.08
2026.07
83.2973.22
81.161.32
2026.07
80.2160.8
2026.07
78.4668.21
2026.07
78.4660.11
2026.07
72.7454.42
2026.07
65.753.87
58.6842.19
2026.07
53.4139.75