VECTOR WIREAI INTELLIGENCE
UTC
Refresh Models Deals Regulatory Sources

Command A+ vs Step 5 Preview

11 SHARED BENCHMARKS

Across 11 shared benchmarks, Command A+ scores higher on 1 and Step 5 Preview on 10. The widest gap is OmniScience Accuracy, where Step 5 Preview scores 41.5 against 8.9.

COHEREVSSTEPFUN11 SHARED110 HEAD-TO-HEADNEWEST SCORE ADDED
AA-LCR52.788.3
critpt0.320.9
gdpval053.3
HLE1246.5
MMMU-Pro63.276.4
scicode38.558.9
terminalbenchV400.533.3

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.