List your company

LLM Safety and Utility Evaluation Suite (StrongReject, AdvBench, IFeval, MMLU) (test)

99.8Safety Scorelat
51.4463.99576.5589.105Feb 12, 2026

Evaluation results

MethodLinks
latModel=llama-3.1-8b-it2026.0299.835.931.617.458.7
CC-DeltaModel=gemma-2-2b-it, steering_strength=1002026.0299.632.419.825.551.8
linearactModel=qwen-2.5-7b-it, steering_strength=1002026.0299.414.72.717.124.2
caaModel=gemma-2-2b-it, steering_strength=1002026.0299.318.16.125.222.9
caaModel=gemma-2-9b-it, steering_strength=1002026.0299.323.620.327.622.9
latModel=gemma-2-9b-it2026.0299.360.886.125.770.5
CC-DeltaModel=llama-3.1-8b-it, steering_strength=1002026.0299.331.2029.464.4
CC-DeltaModel=qwen-2.5-7b-it, steering_strength=1002026.0299.236.56.13073.4
CC-DeltaModel=gemma-2-9b-it, steering_strength=1002026.0298.921.9024.341.5
linearactModel=llama-3.1-8b-it, steering_strength=1002026.0298.817.40.326.525.3
linearactModel=gemma-2-9b-it, steering_strength=1002026.0298.615.51.82024.6
linearactModel=gemma-2-2b-it, steering_strength=1002026.0297.624.227.821.723.1
caaModel=llama-3.1-8b-it, steering_strength=1002026.0297.634.92.436.366.1
caaModel=qwen-2.5-7b-it, steering_strength=1002026.0297.535.712.930.363.9
latModel=gemma-2-2b-it2026.0291.365.595.244.656.7
cbModel=gemma-2-9b-it2026.0287.436.83.33572
cbModel=qwen-2.5-7b-it2026.0286.250.71.97773.1
cbModel=gemma-2-2b-it2026.0283.234.60.946.356.5
latModel=qwen-2.5-7b-it2026.0279.583.110076.572.7
self_reminderModel=llama-3.1-8b-it2026.0277.384.210084.867.9
cbModel=llama-3.1-8b-it2026.0274.384.499.485.368.4
CC-DeltaModel=llama-3.1-8b-it, steering_strength=102026.0274.180.395.977.767.4
CC-DeltaModel=gemma-2-9b-it, steering_strength=102026.0270.580.599.971.969.6
CC-DeltaModel=qwen-2.5-7b-it, steering_strength=102026.0270.479.59272.873.7
caaModel=gemma-2-9b-it, steering_strength=102026.0270.180.710073.169.1
linearactModel=qwen-2.5-7b-it, steering_strength=102026.0268.881.699.57471.3
originalModel=llama-3.1-8b-it2026.0267.584.299.884.568.2
caaModel=llama-3.1-8b-it, steering_strength=102026.0267.484.299.984.468.2
self_reminderModel=qwen-2.5-7b-it2026.0264.185.11008273.2
self_reminderModel=gemma-2-9b-it2026.0263.884.210080.672
CC-DeltaModel=gemma-2-2b-it, steering_strength=102026.0263.370.710056.455.8
linearactModel=gemma-2-9b-it, steering_strength=102026.0260.982.510076.770.7
caaModel=gemma-2-2b-it, steering_strength=102026.0260.470.599.955.955.5
self_reminderModel=gemma-2-2b-it2026.0260.174.810067.756.5
caaModel=qwen-2.5-7b-it, steering_strength=102026.0257.380.897.371.573.6
linearactModel=gemma-2-2b-it, steering_strength=102026.0256.272.510060.656.9
originalModel=gemma-2-9b-it2026.0256.284.410081.172.3
originalModel=gemma-2-2b-it2026.0253.974.210065.756.8
originalModel=qwen-2.5-7b-it2026.0253.384.799.880.274.3