invokeable()
← comparisons / gemini-3.7-flash-vs-mistral-medium-2604

Gemini 3.7 Flash vs Mistral Medium 3.5

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

01Head to head

Gemini 3.7 FlashMistral Medium 3.5
CreatorGoogleMistral AI
Released2026-08-132026-04-29
Context1M262K
Max output66K262K
Input $/M——
Output $/M——
Knowledge cutoff2026-03—
Modalitiestext + image + video + audio → texttext + image → text
Capabilitiestool-use, extended-thinking, structured-outputtool-use, extended-thinking, structured-output
ProvidersGemini API (AI Studio)Mistral AI (La Plateforme)

02Benchmarks · vendor-reported unless verified

Gemini 3.7 FlashMistral Medium 3.5
AutomationBench (accuracy)30.4—
DeepSWE65.3%—
FrontierCode (score)43.6—
GDM-MRCR (accuracy)97—
GDP.pdf (accuracy)34—
SWE-bench Verified (resolved)—77.6
Terminal-Bench (accuracy)85.8—
τ³-Telecom (accuracy)—91.4