LLaMA 13B (0-shot)

Reported on 5 benchmarks across 4 tasks · 1 paper

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

Natural Language Processing5 results

Question AnsweringonPIQA
Accuracy· 2023-02-27
80.1
best: 90.1 (Unicorn 11B (fine-tuned))
LLaMA: Open and Efficient Foundation Language Models arXiv:2302.13971
Code GenerationonMBPP
Accuracy· 2023-02-27
22
best: 96.6 (EG-CFG (DeepSeek-V3-0324))
LLaMA: Open and Efficient Foundation Language Models arXiv:2302.13971
Common Sense ReasoningonWinoGrande
Accuracy· 2023-02-27
73
best: 96.1 (ST-MoE-32B 269B (fine-tuned))
LLaMA: Open and Efficient Foundation Language Models arXiv:2302.13971
Common Sense ReasoningonARC (Easy)
Accuracy· 2023-02-27
74.8
best: 95.2 (ST-MoE-32B 269B (fine-tuned))
LLaMA: Open and Efficient Foundation Language Models arXiv:2302.13971
Sentence CompletiononHellaSwag
Accuracy· 2023-02-27
79.2
best: 96.1 (CompassMTL 567M with Tailor)
LLaMA: Open and Efficient Foundation Language Models arXiv:2302.13971