Skip to content
SOLVENCY

Head to head

Gemini 3.1 Pro (preview) vs Mistral Medium 3.5

Gemini 3.1 Pro (preview): currentMistral Medium 3.5: currentheavy tier

No verdict

Cost per solved task needs a published pass rate for both models. At least one has none, so it is reported as missing rather than estimated.

Source: Scale SEAL leaderboard, SWE-bench Pro · verified 2026-08-21 · prices from each provider's pricing page

Input $/M tokens

lower is better

  • Gemini 3.1 Pro (preview)$2
  • Mistral Medium 3.5$1.5

Output $/M tokens

lower is better

  • Gemini 3.1 Pro (preview)$12
  • Mistral Medium 3.5$7.5

Cost per solved task

needs a pass rate for both

  • Gemini 3.1 Pro (preview)$4.30
  • Mistral Medium 3.5missing
Gemini 3.1 Pro (preview)Mistral Medium 3.5
Input $/Mtok$2$1.5
Output $/Mtok$12$7.5
Cached input $/Mtok$0.2missing
Pass rate46%missing
Pass rate sourceSEALmissing
Cost basismodelledmissing
Cost per solved task$4.30missing

verified 2026-08-21 · heavy task tier; measured rows ignore the tier· Methodology· Gemini 3.1 Pro (preview)· Mistral Medium 3.5