invokeable()
← comparisons / claude-opus-5-vs-mistral-medium-2604

Claude Opus 5 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

Claude Opus 5Mistral Medium 3.5
CreatorAnthropicMistral AI
Released2026-07-242026-04-29
Context1M262K
Max output128K262K
Input $/M——
Output $/M——
Knowledge cutoff2026-05—
Modalitiestext + image → texttext + image → text
Capabilitiestool-use, extended-thinkingtool-use, extended-thinking, structured-output
ProvidersAnthropic APIMistral AI (La Plateforme)

02Benchmarks · vendor-reported unless verified

Claude Opus 5Mistral Medium 3.5
DeepSWE68.8%—
FrontierCode (mean@5)53.4—
SWE-bench Multilingual89.5%—
SWE-bench Multimodal59.4%—
SWE-bench Pro79.2%—
SWE-bench Verified (resolved)9677.6
τ³-Telecom (accuracy)—91.4