Task

Detailed breakdown of individual task performance across different models.

Task Name (15 tasks)
claude-4-6-sonnet
gemini-3-flash
gemini-3.1-pro
gpt-5.2-codex
145.5s115.9s133.5s141.6s
144.2s59.1s119.5s89.0s
159.6s69.0s180.8s98.2s
193.5s152.0s86.9s99.1s
145.2s90.5s63.7s97.6s
92.2s121.2s168.8s39.8s
66.3s119.5s104.6s67.2s
94.9s90.4s147.5s394.7s
77.6s64.4s59.0s78.6s
135.4s146.1s280.2s95.6s
123.7s61.6s48.7s78.5s
74.8s59.1s51.6s82.4s
80.8s70.5s74.0s82.9s
72.1s66.9s107.8s91.0s
80.1s116.6s61.3s84.2s