Model

Llama 3.3

Meta · open weights

Coding

Benchmark	Score	Metric	Harness	Source	Confidence	Link
Web-Bench	6.6	pass@1	N/A	Independent	medium	arxiv.org

Benchmark	Score	Metric	Harness	Source	Confidence	Link
Logbook	0.2	f1	cascaded (msclap)	Independent	medium	arxiv.org
Logbook	0.2	f1	cascaded (enclap)	Independent	medium	arxiv.org