List your company

Bias Evaluation on KoBBQ

98.3Ambiguous Context ScoreQwen3-30B-A3B
38.60454.10269.685.098Sep 24, 2025Oct 23, 2025Nov 21, 2025Dec 21, 2025Jan 19, 2026Feb 17, 2026Mar 19, 2026

Evaluation results

MethodLinks
Qwen3-30B-A3BReasoning=On2026.0398.390.7294.51
EXAONE-4.0-32BReasoning=On2026.0397.293.2395.21
Mi:dm K 2.5 Pro (March ‘26)Reasoning=On2026.0394.5693.4494
Qwen3-30B-A3BReasoning=Off2026.0391.7582.8687.3
Mi:dm K 2.5 Pro (March ‘26)Reasoning=Off2026.0391.0294.1292.57
EXAONE 3.5Size=32B2025.0987.992.190
HyperCLOVAX-SEED-Think-32BReasoning=Off2026.0386.4988.2587.37
Exaone-3.5-7.8B-instParameters=7.8B, Type=Instruction-tuned2026.0185.9173.5479.72
EXAONE 3.5Size=7.8B2025.0985.973.579.7
Mi:dm 2.0 Base-instType=Instruction-tuned2026.0182.380.5481.42
Mi:dm 2.0-BaseScale=Base2025.0982.380.581.4
HyperCLOVAX-SEED-Think-32BReasoning=On2026.0380.4465.5673
EXAONE-4.0-32BReasoning=Off2026.0378.4591.6685.05
Mi:dm 2.0 Mini-instType=Instruction-tuned2026.0155.1155.1755.14
Exaone-3.5-2.4B-instParameters=2.4B, Type=Instruction-tuned2026.0154.1868.1961.18
Llama-3.1-8B-instParameters=8B, Type=Instruction-tuned2026.0140.9257.749.3
Llama-3.1Size=8B2025.0940.957.749.3