AutomationBench
Zapier / Professional work · Completing automated workflows across office software
Across e/accUnder observation
Evidence budgetNot scored
Upstream data timeUnverified
Last successful syncCollection not started
What it measures and how
Compare only configurations on the same official private test set. Fable 5.1 rows with Opus 5 fallback must be excluded.
How this evidence is used
Under observation: public tasks are not official private leaderboard data. Stable exports and mixed-model flags need confirmation.
Limitations and attribution
Under observation: public tasks are not official private leaderboard data. Stable exports and mixed-model flags need confirmation.
Data license: Leaderboard data usage terms remain to be confirmed.
Results are published by Zapier. Raw scores and the e/acc consensus index use different scales and cannot be added directly.