Reported in recent model launches
These model reports include this benchmark. Their harnesses, task subsets, scoring policies, and resource budgets can differ; follow each report’s evaluation notes before joining the numbers.
What it measures
Business workflows require an agent to coordinate real tools and leave the simulated business systems in the required final state.
How to read the result
The original benchmark uses deterministic success checks. Compare complete workflow success with task cost and inspect the model’s effort setting and any fallback models.
Limits and comparison traps
This is the original Zapier implementation. AutomationBench-AA is a separate evaluation contract. Release 1.0.6 results and lab-run adaptations need their own source labels.
Benchmark reference notes
Multi-app SaaS workflow automation benchmark measuring objective completion without guardrail violations.
Where this fits in an evaluation suite
A transcript that says “done” is weaker evidence than the verified final state. Track policy violations, recoveries, and invalid attempts alongside success.
Start with a capability hypothesis, then choose a second test with a different failure mode. Keep the checkpoint, reasoning effort, agent tools, sampling policy, and scoring procedure fixed when measuring a training intervention. Record failures and missing outputs in the denominator.
A reproducible comparison
Pin the benchmark release, task split, model configuration, tools, sampling budget, and evaluation harness described by the primary source.
Publish the exact run configuration, item coverage, score units, and available uncertainty. If a source supplies only an aggregate or a single run, preserve that limit. A new model name or a rounded score alone does not establish a capability improvement.
PRIMARY EVIDENCE & FURTHER READING
Reviewed 2026-10-26. Explanation and interpretation by RLTasks. Benchmark ownership remains with its original authors.