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
Output $/M tokens
lower is better
Cost per solved task
needs a pass rate for both
| Gemini 3.1 Pro (preview) | Mistral Medium 3.5 | |
|---|---|---|
| Input $/Mtok | $2 | $1.5 |
| Output $/Mtok | $12 | $7.5 |
| Cached input $/Mtok | $0.2 | missing |
| Pass rate | 46% | missing |
| Pass rate source | SEAL | missing |
| Cost basis | modelled | missing |
| Cost per solved task | $4.30 | missing |
verified 2026-08-21 · heavy task tier; measured rows ignore the tier· Methodology· Gemini 3.1 Pro (preview)· Mistral Medium 3.5