TokenPost topic

WorkBuddy-Bench

1 TokenPost story is tagged WorkBuddy-Bench. The newest appear first.

Latest WorkBuddy-Bench stories

• Google Research Releases Harness² as GLM-5 Average Score Gains 11.5 Points

  GLM-5’s average WorkBuddy-Bench score rose from 64.2 to 75.7 after one optimization round without retraining the model.

  Oct 19, 2026, 4:08 AM EDT · Technology