List your company

Knowledge Evaluation on KMMLU, KMMLU Pro, GPQA Diamond, and Related Benchmarks

85.1AccuracyDeepSeek-V3.1
47.34857.14966.9576.751Jan 14, 2026

Evaluation results

MethodLinks
DeepSeek-V3.1Thinking Mode=true, Parameters=685B-A37B, Lang=English, Sub-Dataset=MMLU-Pro2026.0185.1
A.X K1Thinking Mode=true, Parameters=519B-A33B, Lang=Korean, Sub-Dataset=CLIcK2026.0184.9
GLM-4.6Thinking Mode=true, Parameters=357B-A32B, Lang=Korean, Sub-Dataset=CLIcK2026.0184.9
DeepSeek-V3.1Thinking Mode=true, Parameters=685B-A37B, Lang=Korean, Sub-Dataset=CLIcK2026.0184.5
GLM-4.6Thinking Mode=true, Parameters=357B-A32B, Lang=English, Sub-Dataset=MMLU-Pro2026.0182.9
A.X K1Thinking Mode=true, Parameters=519B-A33B, Lang=English, Sub-Dataset=MMLU-Pro2026.0181.5
A.X K1Thinking Mode=true, Parameters=519B-A33B, Lang=Korean, Sub-Dataset=KMMLU2026.0180.2
GLM-4.6Thinking Mode=true, Parameters=357B-A32B, Lang=Korean, Sub-Dataset=KMMLU2026.0179.9
GLM-4.6Thinking Mode=true, Parameters=357B-A32B, Lang=Korean, Sub-Dataset=KMMLU-Redux2026.0178.2
GLM-4.6Thinking Mode=true, Parameters=357B-A32B, Lang=English, Sub-Dataset=GPQA Diamond2026.0178
A.X K1Thinking Mode=true, Parameters=519B-A33B, Lang=Korean, Sub-Dataset=KMMLU-Redux2026.0177.9
DeepSeek-V3.1Thinking Mode=true, Parameters=685B-A37B, Lang=English, Sub-Dataset=GPQA Diamond2026.0177.9
DeepSeek-V3.1Thinking Mode=true, Parameters=685B-A37B, Lang=Korean, Sub-Dataset=KMMLU2026.0176.5
DeepSeek-V3.1Thinking Mode=true, Parameters=685B-A37B, Lang=Korean, Sub-Dataset=KMMLU-Redux2026.0175.9
A.X K1Thinking Mode=true, Parameters=519B-A33B, Lang=English, Sub-Dataset=GPQA Diamond2026.0174
GLM-4.6Thinking Mode=true, Parameters=357B-A32B, Lang=Korean, Sub-Dataset=KMMLU-Pro2026.0171.8
DeepSeek-V3.1Thinking Mode=true, Parameters=685B-A37B, Lang=Korean, Sub-Dataset=KMMLU-Pro2026.0171.4
A.X K1Thinking Mode=true, Parameters=519B-A33B, Lang=Korean, Sub-Dataset=KMMLU-Pro2026.0168.1
DeepSeek-V3.1Thinking Mode=true, Parameters=685B-A37B, Lang=Korean, Sub-Dataset=KoBALT2026.0159.7
GLM-4.6Thinking Mode=true, Parameters=357B-A32B, Lang=Korean, Sub-Dataset=KoBALT2026.0159.2
A.X K1Thinking Mode=true, Parameters=519B-A33B, Lang=Korean, Sub-Dataset=KoBALT2026.0148.8