Back to rankings
Anthropic: Claude Sonnet 5.5
Flexprice model metrics · updated Oct 4, 2026.
Capability
96.9
Benchmark and model features
Preference
92.2
Developer selection and Arena
Adoption
82.3
Monthly model usage
Flexprice Index
91.6
Public signals only
Models with Flexprice task results: 30% capability + 25% preference + 20% adoption + 25% Flexprice tasks. Models without task results: 40% capability + 35% preference + 25% adoption. The Index is a composite, not a standalone contract-extraction accuracy score. Read the methodology.