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

Safety Evaluation on RMCBench

1.13ASR

CodeShield

-2.24620.54243.3366.118Jun 10, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
1.130.55
2026.06
3.662.2
2026.06
4.951.83
2026.06
6.043.66
2026.06
7.694.4
2026.06
7.883.11
2026.06
11.542.75
2026.06
23.6310.26
2026.06
26.9223.26
2026.06
36.2619.78
2026.06
48.934.62
2026.06
52.9333.15
2026.06
60.2636.45
2026.06
63.3738.83
2026.06
74.1847.62
2026.06
78.2151.83
2026.06
82.7862.09
2026.06
85.5363.37