List your company

Code Reasoning on LiveCodeBench (Avg@16, Pass@16)

43.2Avg@16ResRL
28.95232.65136.3540.049Oct 16, 2025Nov 17, 2025Dec 20, 2025Jan 22, 2026Feb 24, 2026Mar 29, 2026May 1, 2026

Evaluation results

MethodLinks
ResRLBackbone=Qwen3-4B2026.0543.259.9
FlowRLBackbone=Qwen3-4B2026.0542.458.7
DAPOBackbone=Qwen3-4B2026.054152.3
GRPOBackbone=Qwen3-4B2026.0539.555.1
CaSPModel=DeepSeek-R1-Distill-Qwen-7B2025.1036.0254.48
GRPOModel=DeepSeek-R1-Distill-Qwen-7B2025.1033.9253.41
LAD2026.0233.5151.97
FlowRL2026.0233.2451.61
NSRBackbone=Qwen3-4B2026.0532.852.3
EntAdv2026.0232.7550.9
GRPO2026.0232.4651.25
ClipCov2026.0232.151.97
Base ModelModel=DeepSeek-R1-Distill-Qwen-7B2025.1030.8547.31
BackboneBackbone=Qwen3-4B2026.0530.540.9
KLCov2026.0229.550.18