OpenCodePapers

multiple-choice-question-answering-mcqa-on-30

Question AnsweringMultiple Choice Question Answering (MCQA)
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
PaperCodeAccuracyModelNameReleaseDate
PaLM 2 Technical Report✓ Link90PaLM 2 (few-shot, k=3, Direct)2023-05-17
PaLM 2 Technical Report✓ Link83.6PaLM 2 (few-shot, k=3, CoT)2023-05-17
BloombergGPT: A Large Language Model for Finance✓ Link76PaLM 540B (few-shot, k=3)2023-03-30
BloombergGPT: A Large Language Model for Finance✓ Link56Bloomberg GPT (few-shot, k=3)2023-03-30
BloombergGPT: A Large Language Model for Finance✓ Link54.8BLOOM 176B (few-shot, k=3)2023-03-30
BloombergGPT: A Large Language Model for Finance✓ Link54GPT-NeoX (few-shot, k=3)2023-03-30
BloombergGPT: A Large Language Model for Finance✓ Link52.8OPT 66B (few-shot, k=3)2023-03-30
Training Compute-Optimal Large Language Models✓ Link47.1Chinchilla-70B (few-shot, k=5)2022-03-29
Scaling Language Models: Methods, Analysis & Insights from Training Gopher✓ Link38.6Gopher-280B (few-shot, k=5)2021-12-08