HyperAI

Common Sense Reasoning On Big Bench

Métriques

Accuracy

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle
Accuracy
Paper TitleRepository
BLOOM 176B (few-shot, k=3)40.4BloombergGPT: A Large Language Model for Finance-
Gopher-280B (few-shot, k=5)45.5Scaling Language Models: Methods, Analysis & Insights from Training Gopher
GPT-NeoX 20B (few-shot, k=3)40.8BloombergGPT: A Large Language Model for Finance-
Bloomberg GPT 50B (few-shot, k=3)34BloombergGPT: A Large Language Model for Finance-
PaLM 2 (few-shot, k=3, CoT)77.6PaLM 2 Technical Report
PaLM 540B (few-shot, k=3)60.8BloombergGPT: A Large Language Model for Finance-
PaLM 2 (few-shot, k=3, Direct)78.8PaLM 2 Technical Report
OPT 66B (few-shot, k=3)40.4BloombergGPT: A Large Language Model for Finance-
Chinchilla-70B (few-shot, k=5)54.7Training Compute-Optimal Large Language Models
0 of 9 row(s) selected.