List your company

Code Generation on MBPP Plus 3-shot (test)

42.6Pass@1ESPO
31.36834.28437.240.116Dec 3, 2025

Evaluation results

MethodLinks
ESPOSequence Length=512, Few-shot=32025.1242.6—
ESPOSequence Length=256, Few-shot=32025.1241.6—
LLaDA-1.5Sequence Length=256, Few-shot=32025.1240.4—
diffu-GRPO(d1)Sequence Length=512, Few-shot=32025.1239.4—
ESPOSequence Length=128, Few-shot=32025.1238.9—
LLaDA-1.5Sequence Length=128, Few-shot=32025.1238.8—
LLaDASequence Length=512, Few-shot=32025.1237.8—
LLaDA-1.5Sequence Length=512, Few-shot=32025.1237.3—
LLaDASequence Length=128, Few-shot=32025.1236.8—
LLaDASequence Length=256, Few-shot=32025.1236.8—
wd1Sequence Length=512, Few-shot=32025.1235.6—
diffu-GRPO(d1)Sequence Length=256, Few-shot=32025.1234.8—
wd1Sequence Length=256, Few-shot=32025.1232.8—
diffu-GRPO(d1)Sequence Length=128, Few-shot=32025.1231.8—
wd1Sequence Length=128, Few-shot=32025.1231.8—
diffu-GRPO(d1)Few-shot=32025.12—35.3
ESPOFew-shot=32025.12—41
LLaDAFew-shot=32025.12—37.1
LLaDA-1.5Few-shot=32025.12—38.8
wd1Few-shot=32025.12—33.4