Recipe Scaler Bench
Go to Recipe Scaler
Results
About
RU
System
Light
Dark
Night
DeepSeek V4 Pro, Max Reasoning (1) (OpenCode)
GLM 5.1 (z.ai coding plan) (Cursor)
DeepSeek V4 Pro, Max Reasoning (2) (OpenCode)
Tokens:
2.5M
Cost:
$0.05
24 Apr 2026
Failed tools
DeepSeek is very cheap, but managed only once. Mobile is watchable