Noometry

Model comparison

Mistral Medium 3.5 vs Step 3.5 Flash

Step 3.5 Flash is the stronger model overall, scoring 42.3 to 40.2 on the Noometry Index.

Last verified . 17 shared benchmarks.

Mistral Medium 3.5 Mistral AI

40.2

Rank #152 Confirmed

Step 3.5 Flash StepFun

42.3

Rank #116 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Mistral Medium 3.5 scores higher in 4 categories and Step 3.5 Flash in 4 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in coding, where Step 3.5 Flash leads 42.4 to 36.0.
  • The biggest single-benchmark swing is NYT Connections (extended): 12.9% for Mistral Medium 3.5 and 28.4% for Step 3.5 Flash.
  • Step 3.5 Flash is cheaper at $0.10 / $0.30 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium 3.5.
  • Mistral Medium 3.5 accepts more context: 262K tokens versus 256K.

Side by side

Mistral Medium 3.5Step 3.5 Flash
ProviderMistral AIStepFun
Noometry Index40.242.3
Released—2026-01-29
WeightsOpenOpen
Context window262K256K
Max output210K256K
Input $ / M tokens$1.50$0.10
Output $ / M tokens$7.50$0.30
Results tracked2219

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Step 3.5 Flash leads

Mistral Medium 3.5: 36.0 (#213), Step 3.5 Flash: 42.4 (#105)

BenchmarkMistral Medium 3.5Step 3.5 Flash
LMArena Coding14611436
LMArena WebDev1264—

Reasoning Step 3.5 Flash leads

Mistral Medium 3.5: 17.3 (#295), Step 3.5 Flash: 22.2 (#202)

BenchmarkMistral Medium 3.5Step 3.5 Flash
NYT Connections (extended)12.9%28.4%
LMArena Hard Prompts14361411
Kagi LLM Benchmark41.4%—
Epoch Capabilities Index141.35—

Math Step 3.5 Flash leads

Mistral Medium 3.5: 39.1 (#113), Step 3.5 Flash: 42.6 (#84)

BenchmarkMistral Medium 3.5Step 3.5 Flash
LMArena Math14311408
MathArena Final-Answer Competitions—66.8%

Knowledge Too close to call

Mistral Medium 3.5: 40.0 (#126), Step 3.5 Flash: 39.6 (#132)

BenchmarkMistral Medium 3.5Step 3.5 Flash
LMArena Expert14321421

Multimodal Not comparable

Mistral Medium 3.5: 38.3 (#65), Step 3.5 Flash: —

BenchmarkMistral Medium 3.5Step 3.5 Flash
LMArena Vision1223—

Multilingual Mistral Medium 3.5 leads

Mistral Medium 3.5: 51.9 (#100), Step 3.5 Flash: 50.5 (#119)

BenchmarkMistral Medium 3.5Step 3.5 Flash
LMArena Non-English14041385
LMArena Chinese14421447
LMArena French14481421
LMArena German14511405
LMArena Korean13851352
LMArena Russian13951385
LMArena Spanish14091419
LMArena Japanese—1354

Instruction Following Mistral Medium 3.5 leads

Mistral Medium 3.5: 74.6 (#90), Step 3.5 Flash: 73.1 (#124)

BenchmarkMistral Medium 3.5Step 3.5 Flash
LMArena Instruction Following14151385

Long Context Too close to call

Mistral Medium 3.5: 43.2 (#103), Step 3.5 Flash: 42.8 (#117)

BenchmarkMistral Medium 3.5Step 3.5 Flash
LMArena Longer Query14151402

Writing & Preference Too close to call

Mistral Medium 3.5: 58.5 (#117), Step 3.5 Flash: 58.8 (#113)

BenchmarkMistral Medium 3.5Step 3.5 Flash
LMArena Text14211403
LMArena Creative Writing13741357
LMArena Multi-Turn14231405
EQ-Bench 4993—

Frequently asked questions

Is Mistral Medium 3.5 better than Step 3.5 Flash?

Step 3.5 Flash is the stronger model overall, scoring 42.3 to 40.2 on the Noometry Index.

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

Step 3.5 Flash is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Mistral Medium 3.5 lists at $1.50 and $7.50.

Is Mistral Medium 3.5 or Step 3.5 Flash better for coding?

Step 3.5 Flash scores higher on coding benchmarks: 42.4 versus 36.0 in the Noometry coding category.

Which has the bigger context window?

Mistral Medium 3.5 does, with 262K tokens against 256K.

How many benchmarks do Mistral Medium 3.5 and Step 3.5 Flash share?

17 benchmarks have published results for both models. Mistral Medium 3.5 has 22 scored results on Noometry and Step 3.5 Flash has 19.

Related comparisons

Go deeper