List your company

False Refusal Evaluation on ORB-H

97.2CRELS
5.05628.97852.976.822Oct 9, 2025

Evaluation results

MethodLinks
ELSModel=QWEN 3 1.7B2025.1097.2
CASTModel=QWEN 3 1.7B2025.1096.2
AlphaSteerModel=QWEN 3 1.7B2025.1096
SurgicalModel=QWEN 3 1.7B2025.1095.8
AdaSteerModel=QWEN 3 1.7B2025.1095.8
QWEN 3 1.7BModel=QWEN 3 1.7B2025.1095.5
ELSModel=QWEN 3 14B2025.1084.8
AlphaSteerModel=QWEN 3 14B2025.1084.1
AdaSteerModel=QWEN 3 14B2025.1083.7
CASTModel=QWEN 3 14B2025.1083
ELSModel=LLAMA3.1-8B-INST2025.1082.6
SurgicalModel=QWEN 3 14B2025.1082.6
AdaSteerModel=LLAMA3.1-8B-INST2025.1081.1
QWEN 3 14BModel=QWEN 3 14B2025.1081.1
ELSModel=QWEN 3 8B2025.1080.6
AlphaSteerModel=QWEN 3 8B2025.1080.3
CASTModel=QWEN 3 8B2025.1079.5
ELSModel=LLAMA2-7B-CHAT2025.1078.4
AdaSteerModel=QWEN 3 8B2025.1078
SurgicalModel=QWEN 3 8B2025.1077.6
AlphaSteerModel=LLAMA3.1-8B-INST2025.1077.3
SurgicalModel=LLAMA3.1-8B-INST2025.1076.6
AdaSteerModel=LLAMA2-7B-CHAT2025.1075.7
AlphaSteerModel=LLAMA2-7B-CHAT2025.1075
QWEN 3 8BModel=QWEN 3 8B2025.1075
CASTModel=LLAMA3.1-8B-INST2025.1070.3
CASTModel=LLAMA2-7B-CHAT2025.1066.7
SurgicalModel=LLAMA2-7B-CHAT2025.1065.5
LLAMA3.1-8B-INSTModel=LLAMA3.1-8B-INST2025.1057.3
system promptModel=QWEN 3 1.7B2025.1054.2
system promptModel=QWEN 3 14B2025.1050.8
system promptModel=QWEN 3 8B2025.1043.2
system promptModel=LLAMA3.1-8B-INST2025.1041
LLAMA2-7B-CHATModel=LLAMA2-7B-CHAT2025.1014.8
system promptModel=LLAMA2-7B-CHAT2025.108.6