OpenCodePapers

common-sense-reasoning-on-big-bench-date

Common Sense Reasoning
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
PaperCodeAccuracyModelNameReleaseDate
PaLM 2 Technical Report✓ Link91.2PaLM 2 (few-shot, k=3, CoT)2023-05-17
PaLM 2 Technical Report✓ Link74.0PaLM 2 (few-shot, k=3, Direct)2023-05-17
BloombergGPT: A Large Language Model for Finance✓ Link54.8Bloomberg GPT 50B (few-shot, k=3)2023-03-30
BloombergGPT: A Large Language Model for Finance✓ Link53.6PaLM 540B (few-shot,k=3)2023-03-30
Training Compute-Optimal Large Language Models✓ Link52.3Chinchilla-70B (few-shot, k=5)2022-03-29
BloombergGPT: A Large Language Model for Finance✓ Link50.00BLOOM 176B (few-shot, k=3)2023-03-30
BloombergGPT: A Large Language Model for Finance✓ Link49.60OPT 66B (few-shot, k=3)2023-03-30
BloombergGPT: A Large Language Model for Finance✓ Link45.60GPT-NeoX 20B (few-shot, k=3)2023-03-30
Scaling Language Models: Methods, Analysis & Insights from Training Gopher✓ Link44.1Gopher-280B (few-shot, k=5)2021-12-08