Task

Detailed breakdown of individual task performance across different models.

Task Name (11 tasks)
claude-4-6-sonnet
gemini-3.1-pro
glm-4.7
gpt-5.2-codex
gpt-5.2-codex-with-skills
88.6s66.8s334.3s120.7s58.3s
173.5s95.2s199.7s99.3s56.9s
112.1s123.2s251.5s82.6s59.2s
149.9s282.6s351.5s471.7s204.6s
106.3s96.8s171.6s88.8s91.5s
91.9s144.1s130.1s109.9s99.6s
130.6s161.5s201.0s45.6s41.0s
335.2s600.1s600.0s52.4s67.0s
129.0s71.3s318.9s59.6s91.4s
139.5s100.0s91.8s37.9s47.0s
214.1s128.8s166.5s107.4s92.6s