ProgramBench Results: Opus 5 Leads, 0813 Tops Open-Source Models
ProgramBench Vetted results show Claude Opus 5 still leading overall, while the 0813 model emerges as the strongest open-source model. The 'almost' metric, meaning passing at least 95% of test tasks, proved most informative.
2026-08-23 ~ 2026-08-23 · 2 related posts
- ProgramBench Results: Opus 5 Leads, 0813 Emerges as Strongest Open Model — teortaxesTex · 2026-08-23
- 0813 Tops Open Models on ProgramBench Vetted Evaluation — teortaxesTex · 2026-08-23