Favur Evals
favur.dev

Model · Qwen

Qwen Flash qwen3.7

1 appearance · meta-score 70.0/100 · last seen 2026-08-10 · scored under rubric v15

Pooled composite across 1 primary run: 76.3 - no interval, a single run proves nothing about spread provisional: n < 3, treat as unsettled

Agent role scores

Per-agent-role scores for Qwen Flash qwen3.7
Agent roleScore / 10
Sprint-Review Agent8.88
Code-Review Agent8.20
Build Agent7.76
Develop Agent7.59
Orchestrator7.56
Scout Agent6.54
Test Agent6.47
Sprint-Plan Agent6.19
Pseudocode Agent5.62
Code Agent5.28

Run history (primary model)

Runs where Qwen Flash qwen3.7 was the primary model, oldest first
RunSoWDateComposite
Flash qwen3.7circlesAug 202676.3

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.