GPT-4 o1(300b)

Reported on 2 benchmarks across 2 tasks · 1 paper · 2 SOTA

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

Methodology2 results

Transfer LearningonMML
Average (%)· uses extra data· 2024-10-03
87
SOTA
GPT-4o as the Gold Standard: A Scalable and General Purpose Approach to Filter Language Model Pretraining Data arXiv:2410.02755
Multi-Task LearningonMML
Average (%)· uses extra data· 2024-10-03
87
SOTA
GPT-4o as the Gold Standard: A Scalable and General Purpose Approach to Filter Language Model Pretraining Data arXiv:2410.02755