List your company

Code Generation on LiveCodeBench (Difficulty Tiers)

95.9Easy ScoreGRPO
53.57264.56175.5586.539Mar 8, 2026

Evaluation results

MethodLinks
GRPOModel=DS 8B, Training Context=16K, Testing Context=16K2026.0395.932.74.735.4
MicroCoder-GRPOModel=DS 8B, Training Context=16K, Testing Context=16K2026.0395.9389.739.3
MicroCoder-GRPOModel=Qwen3 4B, Training Context=4K, Testing Context=4K2026.0395.335.68.137.7
DAPOModel=DS 8B, Training Context=16K, Testing Context=16K2026.0395.334.66.936.9
MicroCoder-GRPOModel=Qwen3 4B, Training Context=4K, Testing Context=8K2026.0393.636.110.938.7
DAPOModel=Qwen3 4B, Training Context=4K, Testing Context=8K2026.0390.733.29.136.3
GRPOModel=Qwen3 4B, Training Context=4K, Testing Context=8K2026.038933.79.736.3
DAPOModel=Qwen3 4B, Training Context=4K, Testing Context=4K2026.0388.435.67.835.9
Qwen3-4B-InstructTesting Context=8K, RL Algorithm=None2026.0387.831.78.134.7
GRPOModel=Qwen3 4B, Training Context=4K, Testing Context=4K2026.0387.833.78.735.6
Qwen3-4B-InstructTesting Context=4K, RL Algorithm=None2026.0386.631.77.534.1
MicroCoder-GRPOModel=Qwen3 1.7B, Training Context=4K, Testing Context=4K2026.0373.314.42.223.3
MicroCoder-GRPOModel=Qwen3 1.7B, Training Context=4K, Testing Context=8K2026.0370.917.82.824
DAPOModel=Qwen3 1.7B, Training Context=4K, Testing Context=4K2026.0368.68.72.220.4
DAPOModel=Qwen3 1.7B, Training Context=4K, Testing Context=8K2026.0368.68.72.220.4
GRPOModel=Qwen3 1.7B, Training Context=4K, Testing Context=4K2026.036112.51.319.3
GRPOModel=Qwen3 1.7B, Training Context=4K, Testing Context=8K2026.036112.51.319.3
Qwen3-1.7B InstructTesting Context=4K, RL Algorithm=None2026.0355.27.20.916.1
Qwen3-1.7B InstructTesting Context=8K, RL Algorithm=None2026.0355.27.20.916.1