Closed loops, not prompts
LSS YAML → LoopGym SimEnv → Success@k and observed LES.
Leaderboard
Select a task to compare loops.
Task
Chart
| # | Loop | Submitter | LES ↕ | Success@k ↕ | Cost ↕ | Harness | Spec |
|---|
Tasks
Metrics
What LoopBench measures
Reproducible
Five seeds, no API keys on v0.1, auditable specs.
Community scoreboard
External rows credited; human review on merge.
Run your first score
pip install "le-loop-stack>=0.1.0" loopbench loopgym
loopbench run --task LB-CR-1 --spec your-loop.yaml --seeds 0,1,2,3,4 -o results.json
loopbench validate results.json