phi-1.5-web 1.3B (zero-shot)

Reported on 3 benchmarks across 2 tasks · 1 paper

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

Natural Language Processing3 results

Question AnsweringonSIQA
Accuracy· 2023-09-11
53
best: 83.2 (Unicorn 11B (fine-tuned))
Textbooks Are All You Need II: phi-1.5 technical report arXiv:2309.05463
Common Sense ReasoningonWinoGrande
Accuracy· 2023-09-11
74
best: 96.1 (ST-MoE-32B 269B (fine-tuned))
Textbooks Are All You Need II: phi-1.5 technical report arXiv:2309.05463
Common Sense ReasoningonARC (Challenge)
Accuracy· 2023-09-11
44.9
best: 96.4 (GPT-4 (few-shot, k=25))
Textbooks Are All You Need II: phi-1.5 technical report arXiv:2309.05463