See which tools coding agents choose.

Learn which products Claude Code, Codex, and other coding agents recommend for real tasks, and what it takes to become their first choice.

Start now for freeRead the guide ↗

Benchmark real tasks

Give agents open-ended developer tasks and measure which products they recommend and install, without naming yours.

Compare head to head

Run competitive tasks to see how agents decide between you and a named alternative.

See the sources behind each choice

Inspect the research, ranked recommendations, and code changes behind every decision.

FAQs

Gauge runs your tasks in isolated sessions and records which products each agent considers, recommends, and adopts in code. Use open-ended tasks for unaided selection or head-to-head tasks for a competitive decision.

Yes. Hosted Gauge supports recurring measurements and repeated samples across agents and models. Add repository and persona scenarios to see how choices vary with the user’s context.

Gauge supports Claude Code, Codex, OpenCode, Pi, and Antigravity. The hosted Free plan includes open models on OpenCode and a first onboarding run on Claude Code and Codex at no cost. Upgrade to Pro or Enterprise for ongoing Claude Code and Codex runs and access to all supported agents.

Keep exploring

Agent onboarding ↗Agent-ready docs ↗Agents pricing ↗