VECTOR WIREAI INTELLIGENCE
UTC
Refresh Models Deals Regulatory Sources

Claude Mythos 5 vs Claude Mythos 5.1

3 SHARED BENCHMARKS

Across 3 shared benchmarks, Claude Mythos 5 scores higher on 1 and Claude Mythos 5.1 on 2. The widest gap is ProteinGym Hard, where Claude Mythos 5.1 scores 49.3 against 45.8.

ANTHROPICVSANTHROPIC3 SHARED12 HEAD-TO-HEAD
BioMysteryBench (Human Difficult)44.744.1
BioMysteryBench (Human Solvable)90.190.3

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.