Chinchilla 70B (0-shot)

Reported on 4 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.

Natural Language Processing4 results

Question AnsweringonPIQA
Accuracy· 2022-03-29
81.8
best: 90.1 (Unicorn 11B (fine-tuned))
Training Compute-Optimal Large Language Models arXiv:2203.15556
Question AnsweringonBoolQ
Accuracy· 2022-03-29
83.7
best: 99.87 (Mistral-Nemo 12B (HPT))
Training Compute-Optimal Large Language Models arXiv:2203.15556
Common Sense ReasoningonWinoGrande
Accuracy· 2022-03-29
74.9
best: 96.1 (ST-MoE-32B 269B (fine-tuned))
Training Compute-Optimal Large Language Models arXiv:2203.15556
Sentence CompletiononHellaSwag
Accuracy· 2022-03-29
80.8
best: 96.1 (CompassMTL 567M with Tailor)
Training Compute-Optimal Large Language Models arXiv:2203.15556