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

Open-ended Refusal on Open-ended refusal benchmark

8.76Score

TF

7.727.998.268.53Jun 7, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
8.763.85
2026.06
8.723.83
2026.06
8.73.81
2026.06
8.73.43
2026.06
8.663.82
2026.06
8.645.4
2026.06
8.624.79
2026.06
8.625.34
2026.06
8.625.26
2026.06
8.65.75
2026.06
8.65.35
2026.06
8.67.06
2026.06
8.585.28
2026.06
8.585.68
2026.06
8.563.78
2026.06
8.567.62
2026.06
8.545.55
2026.06
8.547.5
2026.06
8.525.3
2026.06
8.523.8
2026.06
8.55.62
2026.06
8.57.48
2026.06
8.55.82
2026.06
8.467.55
2026.06
8.465.75
2026.06
8.424.89
2026.06
8.425.66
2026.06
8.385.66
2026.06
8.385.72
2026.06
8.385.2
2026.06
8.363.69
2026.06
8.347.44
2026.06
8.345.48
2026.06
8.323.68
2026.06
8.37.3
2026.06
8.283.67
2026.06
8.265.7
2026.06
8.225.05
2026.06
8.225.58
2026.06
8.183.65
2026.06
8.185.1
2026.06
8.144.69
2026.06
8.145
2026.06
8.14.73
2026.06
8.16.92
2026.06
8.064.64
2026.06
8.046.95
2026.06
8.025.25
2026.06
8.025.15
2026.06
86.9
2026.06
7.985.18
2026.06
7.945.12
2026.06
7.94.58
2026.06
7.846.88
2026.06
7.765.1