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

Agent Safety on R-Judge

97.3Accuracy

Gemini-3.1-Pro

31.15648.32865.582.672Feb 11, 2026Mar 1, 2026Mar 19, 2026Apr 6, 2026Apr 24, 2026May 12, 2026May 30, 2026
Updated 1d ago

Evaluation Results

MethodLinks
97.397.499.195.7-
95.295.398.792.1-
2026.02
94.2594.6291.6794.58-
2026.02
93.492.13-92.49-
2026.05
93.492.13--92.49
2026.05
93.393.793.194.3-
2026.02
93.2793.4891.4994.77-
2026.02
93.193.7588.2497.16-
2026.02
93.193.6289.895.67-
2026.05
92.5678.43--78.91
2026.02
92.3992.91-92.26-
2026.05
92.3992.91--92.26
2026.05
92.292.791.793.7-
2026.02
92.0792.66-98.12-
2026.05
92.0792.66--98.12
2026.02
92.0193.12-92.17-
2026.05
92.0193.12--92.17
2026.02
91.9592.6388.0797.78-
2026.05
91.892.787.598.5-
2026.05
91.5780.45--82.78
2026.02
91.3991.84-91.26-
2026.05
91.3991.84--91.26
2026.02
91.2492.37-97.87-
2026.05
91.2492.37--97.87
2026.02
91.1493.55-93.52-
2026.05
91.1493.55--93.52
2026.02
90.891.3189.3693.34-
2026.05
90.891.886.897.5-
2026.05
90.490.693.987.6-
2026.05
89.6789.43--75.21
2026.02
89.6690.538695.56-
2026.05
89.589.594.984.7-
2026.02
88.5189.36-93.34-
2026.05
88.5189.36--93.34
2026.02
87.3687.9196.9688.89-
2026.02
86.2186.9685.1188.89-
2026.02
86.2188.2478.9596.04-
2026.02
86.0587.2382.1493.18-
85.687.481.394.5-
85.18780.794.4-
2026.02
85.0685.0688.182.42-
2026.05
818282.181.9-
8184.67498.8-
2026.02
80.4682.8375.9392.01-
2026.05
80.3477.69--76.21
2026.02
79.5974.07-61.37-
2026.02
78.9775.8279.4777.78-
2026.02
78.6470.57-72.21-
2026.05
78.6470.57--72.21
2026.05
75.774.683.367.5-
2026.05
75.58168.698.8-
2026.02
75.3376.96-78.89-
2026.05
75.3376.96--78.89
2026.02
75.2172.96-71.89-
2026.05
75.2172.96--71.89
2026.02
72.4177.3667.2191.26-
2026.05
71.570.47864.1-
2026.02
68.9752.73-59.08-
68.467.673.862.4-
68.465.577.456.8-
2026.02
67.8255.2-53.49-
2026.05
67.8255.2--53.49
2026.02
67.6964.42-55.36-
63.863.268.358.8-
2026.02
61.9249.3281.8235.29-
61.256.769.148.1-
2026.02
57.4753.1661.7646.67-
2026.02
57.4744.7868.1833.33-
2026.02
57.1265.4756.777.45-
2026.02
56.7650.4962.9342.16-
2026.02
56.3264.8155.5677.78-
2026.02
55.1736.9562.9926.14-
2026.05
54.448.560.140.6-
2026.05
54.136.767.625.2-
53.769.553.399.8-
2026.02
53.4659.18-58.1-
2026.05
53.4659.18--58.1
2026.02
52.8728.07-17.78-
2026.05
52.547.257.240.2-
2026.02
51.826.25-16.34-
2026.05
51.826.25--16.34
2026.02
51.7232.2658.8225.74-
2026.02
48.2814.26-12.22-
2026.02
47.9315.62-12.11-
2026.02
46.3116.63-17.33-
2026.05
46.3116.63--17.33
2026.02
45.4543.0140.1637.66-
2026.02
44.8341.3739.5837.36-
2026.02
41.8520.61-14.38-
2026.05
41.8520.61--14.38
40.6923.65.6-
33.720.127.615.8-