invokeable()
← comparisons / deepseek-v4-pro-0813-vs-gemini-3.7-flash

DeepSeek V4 Pro 0813 vs Gemini 3.7 Flash

Side-by-side from the Invokeable directory — provider-attributed pricing, canonical IDs, draft data flagged. Open as a shareable card →

01Head to head

DeepSeek V4 Pro 0813Gemini 3.7 Flash
CreatorDeepSeekGoogle
Released2026-08-122026-08-13
Context1M1M
Max output384K66K
Input $/M——
Output $/M——
Knowledge cutoff—2026-03
Modalitiestext → texttext + image + video + audio → text
Capabilitiestool-use, extended-thinking, structured-outputtool-use, extended-thinking, structured-output
ProvidersDeepSeek APIGemini API (AI Studio)

02Benchmarks · vendor-reported unless verified

DeepSeek V4 Pro 0813Gemini 3.7 Flash
AutomationBench (accuracy)—30.4
DeepSWE—65.3%
FrontierCode (score)—43.6
GDM-MRCR (accuracy)—97
GDP.pdf (accuracy)—34
Terminal-Bench (accuracy)—85.8