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)).
条件
GLM-5.3; exact effort, endpoint and precision are not stated. 2026-11-18按完整模型卡修正单位、指标/题集或协议标注,数字不变。
GLM-5.3 · AutomationBench (v1.0.6) · GLM-5.3模型卡;v1.0.6 · Scores and configurations
GLM-5.3 record for AutomationBench (v1.0.6) · GLM-5.3模型卡;v1.0.6. 1 score record for this release, including 1 exact value (may include historical records). Includes 2 source locations.
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)).
Conditions
GLM-5.3; exact effort, endpoint and precision are not stated. 2026-11-18按完整模型卡修正单位、指标/题集或协议标注,数字不变。