Validated work
COMPLETED USAGE UNITS · HIGHER IS BETTER
Independent AI capacity index
More signal.
Less AI theatre.
UsageBenchmark shows how much useful coding work an AI plan completes before its usage limit. One clear score. Real finished work.
Live results
See what each plan actually delivers.
Higher Usage Units means more completed work from the plan.
Rank by
Configurations
—
Harness × model × effort
Usage Units
—
Validated work published
Attempts
—
Externally checked tasks
Task time
—
Measured task wall time
Comparison graphs
Work versus task time
Higher and farther left is better.
Result details
Compare harness, model, effort, limit, completion, and measured task time.
| # | Harness | Model | Effort | Limit | UU | Completion | Attempts | Task time | UU/hour | Completed UTC |
|---|