List your company

Code Generation on AtCoder

100Easy AccuracyMicroCoder-GRPO
67.96876.28484.692.916Mar 8, 2026

Evaluation results

MethodLinks
MicroCoder-GRPOModel=Qwen3 4B, Training Context=4K, Testing Context=4K2026.03100499.639.7
GRPOModel=Qwen3 4B, Training Context=4K, Testing Context=8K2026.0310045.212.940.6
DAPOModel=Qwen3 4B, Training Context=4K, Testing Context=8K2026.0310043.311.339.3
MicroCoder-GRPOModel=Qwen3 4B, Training Context=4K, Testing Context=8K2026.0310048.112.941.3
GRPOModel=DS 8B, Training Context=16K, Testing Context=16K2026.0310039.45.835.5
DAPOModel=DS 8B, Training Context=16K, Testing Context=16K2026.0310044.28.337.9
MicroCoder-GRPOModel=DS 8B, Training Context=16K, Testing Context=16K2026.0310043.31038.6
GRPOModel=Qwen3 4B, Training Context=4K, Testing Context=4K2026.0398.146.211.739.7
DAPOModel=Qwen3 4B, Training Context=4K, Testing Context=4K2026.0397.1491039.3
Qwen3-4B-InstructTesting Context=4K, RL Algorithm=None2026.0395.244.29.237.3
Qwen3-4B-InstructTesting Context=8K, RL Algorithm=None2026.0395.245.21037.9
MicroCoder-GRPOModel=Qwen3 1.7B, Training Context=4K, Testing Context=4K2026.0383.7242.926.6
MicroCoder-GRPOModel=Qwen3 1.7B, Training Context=4K, Testing Context=8K2026.0382.726.93.727.5
DAPOModel=Qwen3 1.7B, Training Context=4K, Testing Context=4K2026.0376.915.42.923
DAPOModel=Qwen3 1.7B, Training Context=4K, Testing Context=8K2026.0376.915.42.923
GRPOModel=Qwen3 1.7B, Training Context=4K, Testing Context=4K2026.0370.220.21.721.9
GRPOModel=Qwen3 1.7B, Training Context=4K, Testing Context=8K2026.0370.220.21.721.9
Qwen3-1.7B InstructTesting Context=4K, RL Algorithm=None2026.0369.210.61.319.2
Qwen3-1.7B InstructTesting Context=8K, RL Algorithm=None2026.0369.210.61.319.2