The card says reasoning_effort defaults to max and recommends keeping that default for benchmark reproduction. **AutomationBench**: We evaluate on AutomationBench **v1.0.6**, incorporating the fix for the `null`-type handling issue introduced in [PR #13]([#](https://github.com/zapier/AutomationBench/pull/13)).
AutomationBench (v1.0.6) · GLM-5.3模型卡;v1.0.6 · Reported score · The card says reasoning_effort defaults to max and recommends keeping that default for benchmark reproduction. **AutomationBench**: We evaluate on AutomationBench **v1.0.6**, incorporating the fix for the `null`-type handling issue introduced in [PR #13]([#](https://github.com/zapier/AutomationBench/pull/13)).
Regular display scope. Rankings are grouped by metric and evaluation protocol. Recorded tool access, budgets, and frameworks are shown separately. Scores remain available for reference when conditions are unspecified.
Reported score
The card says reasoning_effort defaults to max and recommends keeping that default for benchmark reproduction. **AutomationBench**: We evaluate on AutomationBench **v1.0.6**, incorporating the fix for the `null`-type handling issue introduced in [PR #13]([#](https://github.com/zapier/AutomationBench/pull/13)).
AutomationBench (v1.0.6) · GLM-5.3模型卡;v1.0.6 · Reported score · The card says reasoning_effort defaults to max and recommends keeping that default for benchmark reproduction. **AutomationBench**: We evaluate on AutomationBench **v1.0.6**, incorporating the fix for the `null`-type handling issue introduced in [PR #13]([#](https://github.com/zapier/AutomationBench/pull/13)).