Skip to main content
Launching the open-source gateway

Mistral Medium 3.5 vs Step 3.5 Flash

SpecMistral Medium 3.5Step 3.5 Flash
Respan Index26.6 (#94)26.5 (#95)
Blended price per 1M$1.5$0.15
Context window256K256K
Input / output per 1M$0.75 / $3.75$0.1 / $0.3
Max output--
Inputtext, visiontext
Released2026-04-282026-02-12

Respan Index by category

Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.

CategoryMistral Medium 3.5Step 3.5 Flash
Coding7.1 Mistral Medium 3.510.7 Step 3.5 Flash
Agents43.7 Mistral Medium 3.523.9 Step 3.5 Flash
Reasoning20.5 Mistral Medium 3.534.6 Step 3.5 Flash
Knowledge & language17.7* Mistral Medium 3.524.8* Step 3.5 Flash
Human preference46.9 Mistral Medium 3.544.6 Step 3.5 Flash

* Estimated: no published scores in that category. How the Respan Index works

Benchmarks both report

Mistral Medium 3.5 leads on 2 of the 2 benchmarks both report. Higher is better. Each score links to where it was published.

BenchmarkMistral Medium 3.5Step 3.5 Flash
LMArena Elo14261393
SWE-bench Verified77.6%74.4%

FAQ

Is Mistral Medium 3.5 better than Step 3.5 Flash?

Mistral Medium 3.5 scores 26.6 on the Respan Index (#94), ahead of Step 3.5 Flash at 26.5 (#95). Mistral Medium 3.5 leads on 2 of the 2 benchmarks both report.

Which is cheaper, Mistral Medium 3.5 or Step 3.5 Flash?

Mistral Medium 3.5 lists at $0.75 input and $3.75 output per 1M tokens; Step 3.5 Flash at $0.1 and $0.3. Step 3.5 Flash is 10x cheaper per token at list price.

Which has the larger context window?

Both accept 256K tokens of context.

Compare other models

vs

Built for AI agents.
Break less.
Ship more.