List your company

Code Generation on ReplicationBench

27.8Pass@3MTL (I)
10.43214.94119.4523.959Apr 15, 2026

Evaluation results

MethodLinks
MTL (I)Model=DeepSeek V3.2, Method=MTL (I)2026.0427.8
Zero-shotModel=DeepSeek V3.2, Method=Zero-shot2026.0426.7
Zero-shotModel=Qwen3-Coder-480B-A35B-Instruct, Method=Zero-shot2026.0421.1
MTL (I)Model=Qwen3-Coder-480B-A35B-Instruct, Method=MTL (I)2026.0421.1
AgentKB#Memories=5,8992026.0420
MTL (I)Model=GPT-5-mini, Method=MTL (I)2026.0418.9
MTL#Memories=4312026.0418.9
MTL (S)Model=GPT-5-mini, Method=MTL (S)2026.0413.3
ReasoningBank#Memories=972026.0413.3
MTL (T)Model=GPT-5-mini, Method=MTL (T)2026.0412.2
Zero-shotModel=GPT-5-mini, Method=Zero-shot2026.0411.1
MTL (W)Model=GPT-5-mini, Method=MTL (W)2026.0411.1
Zeroshot#Memories=-2026.0411.1