Rule 1: Tasks take hours of agent time
Single-turn tasks do not test the flow around the model.
ProjectIn development · not released
For agent tasks that take hours. Existing tests and benchmarks score every run.
| # | Flow | Model | Check | Score |
|---|---|---|---|---|
| 1 | ralph_loop | same | real | --.- |
| 2 | rlar | same | real | --.- |
| 3 | flame_chase | same | real | --.- |
01The gap
Result: a ranking of models
On tasks that take hours, the loop around the model can matter more than the model. FlowBench measures that effect.
02Methodology
Each task runs under every flow, and the same existing check scores every run.
Resulta ranking of flows
Single-turn tasks do not test the flow around the model.
Every task uses a check that already existed: the code runs faster, compiles or passes its tests.
Flows run unchanged in Humanize, the runtime users install.
03Evidence so far
Each comes from one of our other projects, with the model unchanged. These are not FlowBench results.
05Status
The release will be announced in the news and at github.com/humanfia.