Claude Sonnet 4.5 vs Step 5 Preview
11 SHARED BENCHMARKSAcross 11 shared benchmarks, Claude Sonnet 4.5 scores higher on 0 and Step 5 Preview on 11. The widest gap is HLE, where Step 5 Preview scores 46.5 against 19.8. Step 5 Preview is the cheaper of the two on tracked API pricing ($1.00 against $3.00 per million input tokens).
ANTHROPICVSSTEPFUN11 SHARED0–11 HEAD-TO-HEADNEWEST SCORE ADDED
terminalbenchV40033.3
Best tracked score per model per benchmark (default configuration; source-attributed). ↓ marks lower-is-better metrics. Open either model for its full surface, provenance and pricing. Quoted rates are the price-setter row we currently track for each model — its direct or vendor-official listing where one exists (anthropic-official, direct), otherwise the lowest tracked offer.