List your company

Multi-language Programming on Aider-Polyglot

61.7ScoreGPT-o1
16.04427.89739.7551.603Sep 26, 2025

Evaluation results

MethodLinks
GPT-o1Backbone=GPT-o12025.0961.7
CRITIQUE-CODERBackbone=Qwen3-8B, Thinking Mode=true, Training Strategy=CRL2025.0935.6
Qwen3-8B-RLBackbone=Qwen3-8B, Thinking Mode=true, Training Strategy=Standard RL2025.0934.5
Baseline (Qwen3-8B)Backbone=Qwen3-8B, Thinking Mode=true, Training Strategy=Baseline2025.0928.4
CRITIQUE-CODERBackbone=Qwen3-4B, Thinking Mode=true, Training Strategy=CRL2025.0924.4
Qwen3-4B-RLBackbone=Qwen3-4B, Thinking Mode=true, Training Strategy=Standard RL2025.0923.6
Baseline (Qwen3-4B)Backbone=Qwen3-4B, Thinking Mode=true, Training Strategy=Baseline2025.0921.8
DeepSeek-R1-Distill-14BBackbone=DeepSeek-R1-Distill-14B2025.0918.6
DeepCoder-14BBackbone=DeepCoder-14B2025.0918.4
DeepSeek-V2.5-238BBackbone=DeepSeek-V2.5-238B2025.0917.8