List your company

Code Generation on LiveCodeBench v6, HumanEval+, MBPP+, and SciCode

0.992Pass@1DeepSeek-V3.1
0.297280.477640.6580.83836Jan 14, 2026

Evaluation results

MethodLinks
DeepSeek-V3.1Thinking Mode=true, Parameters=685B-A37B, Lang=English, Sub-Dataset=MBPP+2026.010.992
GLM-4.6Thinking Mode=true, Parameters=357B-A32B, Lang=English, Sub-Dataset=MBPP+2026.010.989
DeepSeek-V3.1Thinking Mode=true, Parameters=685B-A37B, Lang=Korean, Sub-Dataset=HumanEval+ ko2026.010.939
A.X K1Thinking Mode=true, Parameters=519B-A33B, Lang=English, Sub-Dataset=MBPP+2026.010.93
A.X K1Thinking Mode=true, Parameters=519B-A33B, Lang=Korean, Sub-Dataset=HumanEval+ ko2026.010.902
A.X K1Thinking Mode=true, Parameters=519B-A33B, Lang=English, Sub-Dataset=HumanEval+2026.010.872
DeepSeek-V3.1Thinking Mode=true, Parameters=685B-A37B, Lang=English, Sub-Dataset=HumanEval+2026.010.86
GLM-4.6Thinking Mode=true, Parameters=357B-A32B, Lang=Korean, Sub-Dataset=HumanEval+ ko2026.010.86
GLM-4.6Thinking Mode=true, Parameters=357B-A32B, Lang=English, Sub-Dataset=HumanEval+2026.010.835
GLM-4.6Thinking Mode=true, Parameters=357B-A32B, Lang=English, Version=25.2.1 - 25.5.1, Sub-Dataset=LiveCodeBench v62026.010.76
A.X K1Thinking Mode=true, Parameters=519B-A33B, Lang=English, Version=25.2.1 - 25.5.1, Sub-Dataset=LiveCodeBench v62026.010.758
A.X K1Thinking Mode=true, Parameters=519B-A33B, Lang=Korean, Sub-Dataset=LiveCodeBench-ko2026.010.731
DeepSeek-V3.1Thinking Mode=true, Parameters=685B-A37B, Lang=English, Version=25.2.1 - 25.5.1, Sub-Dataset=LiveCodeBench v62026.010.695
DeepSeek-V3.1Thinking Mode=true, Parameters=685B-A37B, Lang=Korean, Sub-Dataset=LiveCodeBench-ko2026.010.662
GLM-4.6Thinking Mode=true, Parameters=357B-A32B, Lang=Korean, Sub-Dataset=LiveCodeBench-ko2026.010.559
DeepSeek-V3.1Thinking Mode=true, Parameters=685B-A37B, Lang=English, Sub-Dataset=SciCode2026.010.391
GLM-4.6Thinking Mode=true, Parameters=357B-A32B, Lang=English, Sub-Dataset=SciCode2026.010.384
A.X K1Thinking Mode=true, Parameters=519B-A33B, Lang=English, Sub-Dataset=SciCode2026.010.324