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

General Utility on AirBench 1-10

8.1Speech Score

SARSteer

7.067.337.67.87Oct 20, 2025
Updated 26d ago

Evaluation Results

MethodLinks
2025.10
8.17.277.367.417.53
2025.10
7.727.267.417.397.44
2025.10
7.677.347.367.377.43
2025.10
7.647.087.177.357.31
2025.10
7.637.026.957.277.21
2025.10
7.67.097.137.467.32
2025.10
7.587.0177.27.2
2025.10
7.567.147.077.047.2
2025.10
7.547.37.467.267.39
2025.10
7.526.956.897.057.1
2025.10
7.216.626.666.826.83
2025.10
7.16.46.626.766.72