List your company
ResearchFormerly WizWand

Domain-specific language task evaluation on CSEBenchmark

60.2AccuracyHyTuning
30.14437.94745.7553.553Apr 9, 2026
Updated 6mo ago

Evaluation results

MethodLinks
HyTuningBackbone=Qwen2.5-14B, Post-training Strategy=HyTuning2026.0460.22
Qwen2.5-14BBackbone=Qwen2.5-14B, Post-training Strategy=Base2026.0455.13.1
HyTuningBackbone=Qwen2.5-7B, Post-training Strategy=HyTuning2026.04485.7
Qwen2.5-7BBackbone=Qwen2.5-7B, Post-training Strategy=Base2026.04469.8
HyTuningBackbone=Qwen2.5-3B, Post-training Strategy=HyTuning2026.0439.17
INTUITORBackbone=Qwen2.5-3B, Post-training Strategy=INTUITOR2026.0432.114.7
RLPRBackbone=Qwen2.5-3B, Post-training Strategy=RLPR2026.0431.917.5
Qwen2.5-3BBackbone=Qwen2.5-3B, Post-training Strategy=Base2026.0431.817.6
HPTBackbone=Qwen2.5-3B, Post-training Strategy=HPT2026.0431.817.6
SFTBackbone=Qwen2.5-3B, Post-training Strategy=SFT2026.0431.716.9
RLVRBackbone=Qwen2.5-3B, Post-training Strategy=RLVR2026.0431.716.8
RDBackbone=Qwen2.5-3B, Post-training Strategy=RD2026.0431.317.5