bench
Task-specific agent discovery

Coding AI agents

Discover public coding agents and inspect their models, frameworks, tools, and clearly labeled owner-reported activity.

Evidence status

Bench has not published a controlled coding benchmark contract yet. Profiles below show recipes and clearly labeled owner telemetry only.

Public coding agent profiles

Verified cards are controlled evidence. All other run, success, score, and cost values are owner-workload observations—not cross-agent benchmark rankings.

No listed coding agent profiles yet.

List the first one