Noometry

Model comparison

Mistral Small 3 vs Step 3.5 Flash

Step 3.5 Flash is the stronger model overall, scoring 42.3 to 31.2 on the Noometry Index. Mistral Small 3 costs 2.6× less per token, which makes it the better buy when Step 3.5 Flash's lead doesn't matter for your workload.

Last verified . 16 shared benchmarks.

Mistral Small 3 Mistral AI

31.2

Rank #278 Confirmed

Step 3.5 Flash StepFun

42.3

Rank #116 Confirmed

Summary

  • They share 16 benchmarks with published results for both. Mistral Small 3 scores higher in 0 categories and Step 3.5 Flash in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Step 3.5 Flash leads 58.8 to 32.2.
  • Mistral Small 3 is cheaper at $0.05 / $0.08 per million input/output tokens, against $0.10 / $0.30 for Step 3.5 Flash.
  • Step 3.5 Flash accepts more context: 256K tokens versus 33K.

Side by side

Mistral Small 3Step 3.5 Flash
ProviderMistral AIStepFun
Noometry Index31.242.3
Released2025-01-302026-01-29
WeightsOpenOpen
Context window33K256K
Max output16K256K
Input $ / M tokens$0.05$0.10
Output $ / M tokens$0.08$0.30
Results tracked2419

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

Category by category

Coding Step 3.5 Flash leads

Mistral Small 3: 36.5 (#207), Step 3.5 Flash: 42.4 (#105)

BenchmarkMistral Small 3Step 3.5 Flash
LMArena Coding12461436
BigCodeBench Instruct45.3%—
BigCodeBench Complete50.4%—

Reasoning Step 3.5 Flash leads

Mistral Small 3: 18.9 (#273), Step 3.5 Flash: 22.2 (#202)

BenchmarkMistral Small 3Step 3.5 Flash
LMArena Hard Prompts12331411
NYT Connections (extended)—28.4%
Chess Puzzles0%—
Epoch Capabilities Index127.07—

Math Step 3.5 Flash leads

Mistral Small 3: 16.3 (#295), Step 3.5 Flash: 42.6 (#84)

BenchmarkMistral Small 3Step 3.5 Flash
LMArena Math12401408
MathArena Final-Answer Competitions—66.8%
OTIS Mock AIME 2024-20256.7%—

Knowledge Step 3.5 Flash leads

Mistral Small 3: 25.1 (#263), Step 3.5 Flash: 39.6 (#132)

BenchmarkMistral Small 3Step 3.5 Flash
LMArena Expert12021421
GPQA Diamond47.3%—
Confabulations25.2%—

Multilingual Step 3.5 Flash leads

Mistral Small 3: 37.3 (#236), Step 3.5 Flash: 50.5 (#119)

BenchmarkMistral Small 3Step 3.5 Flash
LMArena Non-English11981385
LMArena Chinese12041447
LMArena French12031421
LMArena German12111405
LMArena Japanese11111354
LMArena Korean11881352
LMArena Russian12161385
LMArena Spanish—1419

Instruction Following Step 3.5 Flash leads

Mistral Small 3: 63.7 (#229), Step 3.5 Flash: 73.1 (#124)

BenchmarkMistral Small 3Step 3.5 Flash
LMArena Instruction Following12141385

Long Context Step 3.5 Flash leads

Mistral Small 3: 37.8 (#211), Step 3.5 Flash: 42.8 (#117)

BenchmarkMistral Small 3Step 3.5 Flash
LMArena Longer Query12461402

Writing & Preference Step 3.5 Flash leads

Mistral Small 3: 32.2 (#280), Step 3.5 Flash: 58.8 (#113)

BenchmarkMistral Small 3Step 3.5 Flash
LMArena Text12341403
LMArena Creative Writing11951357
LMArena Multi-Turn12171405
EQ-Bench Creative Writing707—

Frequently asked questions

Is Mistral Small 3 better than Step 3.5 Flash?

Step 3.5 Flash is the stronger model overall, scoring 42.3 to 31.2 on the Noometry Index. Mistral Small 3 costs 2.6× less per token, which makes it the better buy when Step 3.5 Flash's lead doesn't matter for your workload.

Which is cheaper, Mistral Small 3 or Step 3.5 Flash?

Mistral Small 3 is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; Step 3.5 Flash lists at $0.10 and $0.30.

Is Mistral Small 3 or Step 3.5 Flash better for coding?

Step 3.5 Flash scores higher on coding benchmarks: 42.4 versus 36.5 in the Noometry coding category.

Which has the bigger context window?

Step 3.5 Flash does, with 256K tokens against 33K.

How many benchmarks do Mistral Small 3 and Step 3.5 Flash share?

16 benchmarks have published results for both models. Mistral Small 3 has 24 scored results on Noometry and Step 3.5 Flash has 19.

Related comparisons

Go deeper