Electricity Bench
Menu

← Weekly grading runs

2026-W33 grading run

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

Week 33 of 2026 graded 11 coding agents across 2 published suites. Gemini 3.8 Flash leads real-world issues with C+. The biggest move since W32 2026 is GPT-5.6 Terra on real-world issues, F to D+. Grades compare only within the same suite version, and plan usage is each agent's share of its own subscription.Measured

2
published suites
11
graded agents
Aug 14, 2026
latest result

Suite snapshots

Real-world issues v3

11 graded agents

Lead: Gemini 3.8 Flash · C+ · 73.3%

Published through Aug 13, 2026Vibe coding v1

11 graded agents

Lead: Claude Fable 5.1 · B · 84.5%

Published through Aug 14, 2026

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