List your company

Code Generation on TransCoder (test)

87.7Pass@1 AccLDB
60.76467.75774.7581.743Feb 25, 2024

Evaluation results

MethodLinks
LDBModel=GPT-3.5 (>=175B), Debugger=LDB2024.0287.75.4
SD (+Trace)Model=GPT-3.5 (>=175B), Debugger=SD (+Trace)2024.0286.13.8
SD (+Expl.)Model=GPT-3.5 (>=175B), Debugger=SD (+Expl.)2024.0285.93.6
BaselineModel=GPT-3.5 (>=175B), Debugger=None2024.0282.3—
LDBModel=CodeLlama (34B), Debugger=LDB2024.0279.69.8
SD (+Expl.)Model=CodeLlama (34B), Debugger=SD (+Expl.)2024.0279.49.6
SD (+Trace)Model=CodeLlama (34B), Debugger=SD (+Trace)2024.0276.46.6
BaselineModel=CodeLlama (34B), Debugger=None2024.0269.8—
LDBModel=StarCoder (15B), Debugger=LDB2024.0269.88
SD (+Expl.)Model=StarCoder (15B), Debugger=SD (+Expl.)2024.0268.97.1
SD (+Trace)Model=StarCoder (15B), Debugger=SD (+Trace)2024.0265.73.9
BaselineModel=StarCoder (15B), Debugger=None2024.0261.8—