SimpleQA measures short-form factuality using challenging questions with single, indisputable answers. It evaluates a model’s calibration by classifying responses as correct, incorrect, or not attempted, prioritizing accuracy over generation length.
条件
SimpleQA measures short-form factuality using challenging questions with single, indisputable answers. It evaluates a model’s calibration by classifying responses as correct, incorrect, or not attempted, prioritizing accuracy over generation length.
GLM-5 · SimpleQA · GLM-5固定v2报告/模型卡;版本未注明 · Scores and configurations
GLM-5 record for SimpleQA · GLM-5固定v2报告/模型卡;版本未注明. 1 score record for this release, including 1 exact value (may include historical records). Includes 1 source location.
SimpleQA measures short-form factuality using challenging questions with single, indisputable answers. It evaluates a model’s calibration by classifying responses as correct, incorrect, or not attempted, prioritizing accuracy over generation length.
Conditions
SimpleQA measures short-form factuality using challenging questions with single, indisputable answers. It evaluates a model’s calibration by classifying responses as correct, incorrect, or not attempted, prioritizing accuracy over generation length.