Current theme: dark
← Back to Leaderboard
Task
Detailed breakdown of individual task performance across different models.
Status
All
Models
All
Task Name (10 tasks)
claude-4-6-sonnet
gemini-3.1-pro
glm-4.7
glm-4.7-with-skills
gpt-5.2-codex
create_restore_snapshot
78.1s
209.4s
600.0s
188.4s
139.7s
env_vars_security_check
52.9s
5.1s
105.2s
128.6s
116.1s
manage_nginx_config
103.5s
320.5s
432.7s
78.5s
325.3s
metadata_association
72.8s
167.3s
377.5s
92.2s
82.9s
monitor_background_streaming
86.7s
158.8s
126.7s
428.6s
42.8s
multiple_code_contexts
71.1s
50.9s
266.0s
72.2s
25.8s
python_env_setup_uv
441.2s
220.8s
433.3s
130.2s
65.2s
sdk_basic_sandbox
418.0s
36.9s
600.0s
114.3s
108.9s
security_command_capture
169.2s
317.1s
68.3s
116.2s
198.9s
web_server_public_url
362.4s
119.8s
27.8s
421.0s
24.0s