List your company

Code Generation on MBPP (3) (pass@1)

43.6Pass@1ESPO
34.03236.5163941.484May 28, 2026

Evaluation results

MethodLinks
ESPOSequence Length=1282026.0543.6
GDSDSequence Length=5122026.0543.6
GDSD w/ TLCSequence Length=2562026.0543.6
GDSD w/ TLCSequence Length=Avg.2026.0543.3
ESPOSequence Length=2562026.0543.2
GDSD w/ TLCSequence Length=5122026.0543.2
GDSD w/ TLCSequence Length=1282026.0543
ESPOSequence Length=Avg.2026.0542.7
LLaDASequence Length=2562026.0542
GDSDSequence Length=Avg.2026.0542
GDSDSequence Length=2562026.0541.8
ESPOSequence Length=5122026.0541.2
SPGSequence Length=2562026.0540.8
GDSDSequence Length=1282026.0540.6
SPGSequence Length=Avg.2026.0540.5
SPGSequence Length=1282026.0540.4
SPGSequence Length=5122026.0540.4
LLaDASequence Length=Avg.2026.0538.8
LLaDASequence Length=5122026.0538.1
diffu-GRPO (d1)Sequence Length=5122026.0538
wd1Sequence Length=1282026.0538
wd1Sequence Length=2562026.0537.2
diffu-GRPO (d1)Sequence Length=2562026.0536.6
diffu-GRPO (d1)Sequence Length=Avg.2026.0536.5
wd1Sequence Length=Avg.2026.0536.5
LLaDASequence Length=1282026.0536.2
diffu-GRPO (d1)Sequence Length=1282026.0534.8
wd1Sequence Length=5122026.0534.4