Head to head
DeepSeek V4 Flash vs Mistral Medium 3.5
DeepSeek V4 Flash: 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: Artificial Analysis (artificialanalysis.ai) · 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
| DeepSeek V4 Flash | Mistral Medium 3.5 | |
|---|---|---|
| Input $/Mtok | $0.44 | $1.5 |
| Output $/Mtok | $1.32 | $7.5 |
| Cached input $/Mtok | $0.014 | missing |
| Pass rate | 50% | missing |
| Pass rate source | AA | missing |
| Cost basis | measured | missing |
| Cost per solved task | $0.12 | missing |
verified 2026-08-21 · heavy task tier; measured rows ignore the tier· Methodology· DeepSeek V4 Flash· Mistral Medium 3.5