Task

Detailed breakdown of individual task performance across different models.

Task Name (10 tasks)
claude-4-6-sonnet
gemini-3.1-pro
glm-4.7
glm-4.7-with-skills
gpt-5.2-codex
78.1s209.4s600.0s188.4s139.7s
52.9s5.1s105.2s128.6s116.1s
103.5s320.5s432.7s78.5s325.3s
72.8s167.3s377.5s92.2s82.9s
86.7s158.8s126.7s428.6s42.8s
71.1s50.9s266.0s72.2s25.8s
441.2s220.8s433.3s130.2s65.2s
418.0s36.9s600.0s114.3s108.9s
169.2s317.1s68.3s116.2s198.9s
362.4s119.8s27.8s421.0s24.0s