Noometry

Model comparison

Mistral Medium 3.5 vs Step 5 Preview

Step 5 Preview is the stronger model overall, scoring 47.9 to 40.2 on the Noometry Index.

Last verified . 15 shared benchmarks.

Mistral Medium 3.5 Mistral AI

40.2

Rank #152 Confirmed

Step 5 Preview StepFun

47.9

Rank #58 Confirmed

Summary

  • They share 15 benchmarks with published results for both. Mistral Medium 3.5 scores higher in 0 categories and Step 5 Preview in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Step 5 Preview leads 40.0 to 17.3.
  • Step 5 Preview is cheaper at $1 / $2.70 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium 3.5.
  • Step 5 Preview accepts more context: 1.02M tokens versus 262K.
  • Mistral Medium 3.5 has downloadable open weights; the other is API-only.

Side by side

Mistral Medium 3.5Step 5 Preview
ProviderMistral AIStepFun
Noometry Index40.247.9
Released—2026-09-16
WeightsOpenProprietary
Context window262K1.02M
Max output210K66K
Input $ / M tokens$1.50$1
Output $ / M tokens$7.50$2.70
Results tracked2218

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

Category by category

Coding Step 5 Preview leads

Mistral Medium 3.5: 36.0 (#213), Step 5 Preview: 51.8 (#36)

BenchmarkMistral Medium 3.5Step 5 Preview
LMArena WebDev12641564
LMArena Coding14611480
SciCode—58.9%

Reasoning Step 5 Preview leads

Mistral Medium 3.5: 17.3 (#295), Step 5 Preview: 40.0 (#57)

BenchmarkMistral Medium 3.5Step 5 Preview
LMArena Hard Prompts14361465
Kagi LLM Benchmark41.4%—
NYT Connections (extended)12.9%—
CritPt—20.9%
Epoch Capabilities Index141.35—

Math Step 5 Preview leads

Mistral Medium 3.5: 39.1 (#113), Step 5 Preview: 46.1 (#72)

BenchmarkMistral Medium 3.5Step 5 Preview
LMArena Math14311470
ProofBench—42%

Knowledge Step 5 Preview leads

Mistral Medium 3.5: 40.0 (#126), Step 5 Preview: 41.2 (#112)

BenchmarkMistral Medium 3.5Step 5 Preview
LMArena Expert14321470

Multimodal Step 5 Preview leads

Mistral Medium 3.5: 38.3 (#65), Step 5 Preview: 41.0 (#41)

BenchmarkMistral Medium 3.5Step 5 Preview
LMArena Vision12231267

Multilingual Step 5 Preview leads

Mistral Medium 3.5: 51.9 (#100), Step 5 Preview: 53.8 (#54)

BenchmarkMistral Medium 3.5Step 5 Preview
LMArena Non-English14041432
LMArena Chinese14421519
LMArena Russian13951436
LMArena Spanish14091439
LMArena French1448—
LMArena German1451—
LMArena Korean1385—

Instruction Following Step 5 Preview leads

Mistral Medium 3.5: 74.6 (#90), Step 5 Preview: 76.0 (#50)

BenchmarkMistral Medium 3.5Step 5 Preview
LMArena Instruction Following14151444

Long Context Step 5 Preview leads

Mistral Medium 3.5: 43.2 (#103), Step 5 Preview: 44.5 (#64)

BenchmarkMistral Medium 3.5Step 5 Preview
LMArena Longer Query14151455

Writing & Preference Step 5 Preview leads

Mistral Medium 3.5: 58.5 (#117), Step 5 Preview: 62.8 (#71)

BenchmarkMistral Medium 3.5Step 5 Preview
LMArena Text14211442
LMArena Creative Writing13741410
LMArena Multi-Turn14231447
EQ-Bench 4993—

Frequently asked questions

Is Mistral Medium 3.5 better than Step 5 Preview?

Step 5 Preview is the stronger model overall, scoring 47.9 to 40.2 on the Noometry Index.

Which is cheaper, Mistral Medium 3.5 or Step 5 Preview?

Step 5 Preview is cheaper. It lists at $1 per million input tokens and $2.70 per million output tokens; Mistral Medium 3.5 lists at $1.50 and $7.50.

Is Mistral Medium 3.5 or Step 5 Preview better for coding?

Step 5 Preview scores higher on coding benchmarks: 51.8 versus 36.0 in the Noometry coding category.

Which has the bigger context window?

Step 5 Preview does, with 1.02M tokens against 262K.

How many benchmarks do Mistral Medium 3.5 and Step 5 Preview share?

15 benchmarks have published results for both models. Mistral Medium 3.5 has 22 scored results on Noometry and Step 5 Preview has 18.

Related comparisons

Go deeper