Favur Evals
favur.dev

Model · Anthropic

Anthropic Claude Sonnet 5

5 appearances · meta-score 66.9/100 · last seen 2026-07-23 · scored under rubric v15

Pooled composite across 5 primary runs: 56.3 ± 12.2 (95% CI)

Agent role scores

Per-agent-role scores for Anthropic Claude Sonnet 5
Agent roleScore / 10
Sprint-Review Agent8.17
Develop Agent7.42
Architect7.38
Orchestrator7.09
Code-Review Agent6.72
Build Agent6.66
Platform Agent6.64
Scout Agent6.50
Spec Agent6.38
Sprint-Plan Agent6.35
Test Agent6.01
Code Agent5.86
Pseudocode Agent5.45

Run history (primary model)

Runs where Anthropic Claude Sonnet 5 was the primary model, oldest first
RunSoWDateComposite
Claude Sonnet 5circlesJul 202647.8
Claude Sonnet 5circlesJul 202646.6
Claude Sonnet 5circlesJul 202670.8
Claude Sonnet 5circlesJul 202657.9
Claude Sonnet 5 + Gemini Flash LitesolarSystemJul 202658.3

Every run on Favur Evals is scored by the same deterministic engine, on the same Statements of Work. The benchmark is self-funded — no vendor sponsorship, credits, or grants.