invokeable()

DeepSeek V4 Pro 0813 vs GPT-5.6 Luna

A custom comparison card. Numbers link back to their entries; data as of 2026-08-19. Build your own →

model
DeepSeek V4 Pro 0813
DeepSeek
model
GPT-5.6 Luna
OpenAI
Context1M1.1M
Input $/M
Output $/M
Knowledge cutoff2026-02
Available viaDeepSeek APIOpenAI API
SWE-bench Pro62.7%
Terminal-Bench (success rate)84.7
DeepSWE67.2%
GPQA Diamond (accuracy)92.3
FrontierMath (accuracy)78.6
BrowseComp (accuracy)83.3