Model

Codex 5-shot CoT

OpenAI · closed weights

Knowledge & Reasoning

Benchmark	Score	Metric	Harness	Source	Confidence	Link
medmcqa	62.7	test_set_(acc-%)	N/A	Independent	medium	arxiv.org
medqa	60.2	accuracy	N/A	Independent	medium	arxiv.org
PubMedQA	78.2	accuracy	N/A	Independent	medium	arxiv.org