invokeable()

DeepSeek V4 Pro 0813 vs Mistral Medium 3.5

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
Mistral Medium 3.5
Mistral AI
Context1M262K
Input $/M
Output $/M
Knowledge cutoff
Available viaDeepSeek APIMistral AI (La Plateforme)
SWE-bench Verified (resolved)77.6
τ³-Telecom (accuracy)91.4