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

Agent performance evaluation on Harness-Bench

74.6Combined Score

FairyClaw

49.6456.1262.669.08May 19, 2026
Updated 14d ago

Evaluation Results

MethodLinks
2026.05
74.63.5146.8
2026.05
74.46.2983.8
2026.05
747.2897
2026.05
69.36.0380.4
2026.05
68.96.5887.7
2026.05
68.58.16108.9
2026.05
64.512.7169.3
2026.05
64.36.2783.6
2026.05
63.53.8451.2
2026.05
62.26.2182.8
2026.05
58.76.0981.2
2026.05
50.64.8664.8