phi-1.5-web 1.3B

Reported on 3 benchmarks across 3 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Methodology2 results

Transfer LearningonMML
Average (%)· 2023-09-11
37.9
best: 87 (GPT-4 o1(300b))
Textbooks Are All You Need II: phi-1.5 technical report arXiv:2309.05463
Multi-Task LearningonMML
Average (%)· 2023-09-11
37.9
best: 87 (GPT-4 o1(300b))
Textbooks Are All You Need II: phi-1.5 technical report arXiv:2309.05463

Natural Language Processing1 result

Code GenerationonMBPP
Accuracy· 2023-09-11
43.5
best: 96.6 (EG-CFG (DeepSeek-V3-0324))
Textbooks Are All You Need II: phi-1.5 technical report arXiv:2309.05463