AutomationBench, Zapier private evaluation set release 1.0.6 (AutomationBench (Zapier 1.0.6))
We show this table for reference; we do not rank on it.
An agent benchmark for completing business workflows across simulated applications and API endpoints.
Benchmark score on AutomationBench (Zapier 1.0.6) — September 29, 2026
We compile the AutomationBench (Zapier 1.0.6) rows from provider self-reports. Claude Sonnet 5.5 leads the table at 44.7%. We do not use these results to rank models overall.
1 modelAgenticCurrentDisplay onlyUpdated September 29, 2026
Benchmark score table (1 model)
ScoreAbout AutomationBench (Zapier 1.0.6)
Year
2026
Tasks
Simulated business workflows across 47 applications
Format
Task pass rate
Difficulty
Long-horizon automation
Section 8.14.6 reports Zapier's private release 1.0.6 evaluation set. The Claude Sonnet 5.5 run used API default fallbacks. This lane stays separate from the 600-task public subset and Artificial Analysis AutomationBench-AA.
Freshness and provenance
Version
AutomationBench (Zapier 1.0.6) 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
Questions
What does AutomationBench (Zapier 1.0.6) measure?
An agent benchmark for completing business workflows across simulated applications and API endpoints.
Which model scores highest on AutomationBench (Zapier 1.0.6)?
Claude Sonnet 5.5 by Anthropic currently leads with a score of 44.7% on AutomationBench (Zapier 1.0.6).
How many models are evaluated on AutomationBench (Zapier 1.0.6)?
1 AI models have been evaluated on AutomationBench (Zapier 1.0.6) on BenchLM.
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 2,000+ readers.
One email each week. Unsubscribe anytime.