2026-W34 grading run

One public snapshot for the week, assembled as each suite publishes. Grades compare only within the same suite version.

Week 34 of 2026 graded 12 coding agents across 3 published suites. Claude Haiku 4.5 leads real-world issues with C. The biggest move since W33 2026 is Claude Haiku 4.5 on real-world issues, F to C. Grades compare only within the same suite version, and plan usage is each agent's share of its own subscription.Measured W34 2026

published suites

graded agents

Aug 18, 2026

Suite snapshots

Real-world issues v3

12 graded agents

Lead: Claude Haiku 4.5 · C · 63.3%

Published through Aug 18, 2026 Spec planning v1

12 graded agents

Lead: GPT-6.1 Sol · C · 66.7%

Published through Aug 18, 2026 Vibe coding v1

12 graded agents

Lead: Gemini 3.8 Flash · B- · 79.4%

Published through Aug 18, 2026

A suite can appear here before the others. Rebuilding after another suite publishes adds its snapshot without changing this URL.