GPT-4.1-mini
A lightweight model in OpenAI's GPT-4.1 series, designed to balance cost and performance. It is suited for large-scale annotation and evaluation tasks.
Timeline (last 90 days)
Edu-QuRating uses GPT-4.1-mini as the judge to make pairwise preference judgments on document pairs.
The best-performing Edu-QuRater achieved an average accuracy of 0.917 in reproducing GPT-4.1-mini pairwise judgments on the held-out set.
Sequence classification models are typically based on encoder architectures such as BERT or DeBERTa, with inference costs several orders of magnitude lower than GPT-4.1-mini.
All Facts (3)
Edu-QuRating uses GPT-4.1-mini as the judge to make pairwise preference judgments on document pairs.
50%UnverifiedThe best-performing Edu-QuRater achieved an average accuracy of 0.917 in reproducing GPT-4.1-mini pairwise judgments on the held-out set.
50%UnverifiedSequence classification models are typically based on encoder architectures such as BERT or DeBERTa, with inference costs several orders of magnitude lower than GPT-4.1-mini.
50%