List your company
ResearchFormerly WizWand

Code Generation on CodeForces

24.89Avg@8CodeScaler
4.56849.844215.1220.3958Feb 4, 2026
Updated 8mo ago

Evaluation results

MethodLinks
CodeScalerBase Model=Qwen3-14B-Base, Reward Feedback Source=CodeScaler2026.0224.89
RLVR (Binary)Base Model=Qwen3-14B-Base, Reward Feedback Source=RLVR (Binary)2026.0220.79
CodeScalerTraining Dataset=rStarCoder, Backbone Model=Qwen3-14B, Training Protocol=CodeScaler2026.0219.96
CodeScalerBase Model=Qwen3-8B-Base, Reward Feedback Source=CodeScaler2026.0219.61
RLVR (Binary)Base Model=Qwen3-8B-Base, Reward Feedback Source=RLVR (Binary)2026.0216.43
CodeScalerTraining Dataset=rStarCoder, Backbone Model=Qwen3-8B, Training Protocol=CodeScaler2026.0215.95
RLVR (Binary)Training Dataset=rStarCoder, Backbone Model=Qwen3-14B, Training Protocol=RLVR2026.0215.65
CodeScalerTraining Dataset=KodCode, Backbone Model=Qwen3-14B, Training Protocol=CodeScaler2026.0215.17
RLVR (Binary)Training Dataset=KodCode, Backbone Model=Qwen3-14B, Training Protocol=RLVR2026.0214.1
AceCodeRMBase Model=Qwen3-14B-Base, Reward Feedback Source=AceCodeRM2026.0213.35
RLVR (Binary)Training Dataset=rStarCoder, Backbone Model=Qwen3-8B, Training Protocol=RLVR2026.0213.19
CodeScalerTraining Dataset=KodCode, Backbone Model=Qwen3-8B, Training Protocol=CodeScaler2026.0212.17
RLVR (Binary)Training Dataset=KodCode, Backbone Model=Qwen3-8B, Training Protocol=RLVR2026.0211.64
SkyworkRMBase Model=Qwen3-14B-Base, Reward Feedback Source=SkyworkRM2026.0210.35
AceCodeRMBase Model=Qwen3-8B-Base, Reward Feedback Source=AceCodeRM2026.029.74
Qwen3-14B-BaseTraining Dataset=KodCode, Backbone Model=Qwen3-14B, Training Protocol=Base2026.028.45
Qwen3-14B-BaseTraining Dataset=rStarCoder, Backbone Model=Qwen3-14B, Training Protocol=Base2026.028.45
Qwen3-14B-BaseBase Model=Qwen3-14B-Base, Reward Feedback Source=None (Base)2026.028.45
SkyworkRMBase Model=Qwen3-8B-Base, Reward Feedback Source=SkyworkRM2026.028
Qwen3-8B-BaseTraining Dataset=KodCode, Backbone Model=Qwen3-8B, Training Protocol=Base2026.025.35
Qwen3-8B-BaseTraining Dataset=rStarCoder, Backbone Model=Qwen3-8B, Training Protocol=Base2026.025.35
Qwen3-8B-BaseBase Model=Qwen3-8B-Base, Reward Feedback Source=None (Base)2026.025.35