Noometry

Model comparison

Mistral Large 3 vs Step 3.5 Flash

Step 3.5 Flash is the stronger model overall, scoring 41.7 to 38.6 on the Noometry Index.

Last verified . 18 shared benchmarks.

Mistral Large 3 Mistral AI

38.6

Rank #172 Confirmed

Step 3.5 Flash StepFun

41.7

Rank #116 Confirmed

Summary

  • They share 18 benchmarks with published results for both. Mistral Large 3 scores higher in 4 categories and Step 3.5 Flash in 4 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in coding, where Step 3.5 Flash leads 41.7 to 34.1.
  • The biggest single-benchmark swing is NYT Connections (extended): 7.5% for Mistral Large 3 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 $0.25 / $0.75 for Mistral Large 3.
  • Mistral Large 3 accepts more context: 262K tokens versus 256K.

Side by side

Mistral Large 3Step 3.5 Flash
ProviderMistral AIStepFun
Noometry Index38.641.7
Released2025-12-022026-01-29
WeightsOpenOpen
Context window262K256K
Max output8K256K
Input $ / M tokens$0.25$0.10
Output $ / M tokens$0.75$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 Large 3: 34.1 (#230), Step 3.5 Flash: 41.7 (#106)

BenchmarkMistral Large 3Step 3.5 Flash
LMArena Coding14471436
LMArena WebDev1230—

Reasoning Step 3.5 Flash leads

Mistral Large 3: 14.6 (#314), Step 3.5 Flash: 21.2 (#202)

BenchmarkMistral Large 3Step 3.5 Flash
NYT Connections (extended)7.5%28.4%
LMArena Hard Prompts14291411
Kagi LLM Benchmark50.9%—
Thematic Generalization23%—

Math Step 3.5 Flash leads

Mistral Large 3: 36.0 (#131), Step 3.5 Flash: 40.6 (#77)

BenchmarkMistral Large 3Step 3.5 Flash
LMArena Math14151408
MathArena Final-Answer Competitions—66.8%

Knowledge Step 3.5 Flash leads

Mistral Large 3: 35.5 (#173), Step 3.5 Flash: 39.0 (#127)

BenchmarkMistral Large 3Step 3.5 Flash
LMArena Expert14211422
Vectara Hallucination Rate14.5%—

Multimodal Not comparable

Mistral Large 3: 37.6 (#65), Step 3.5 Flash: —

BenchmarkMistral Large 3Step 3.5 Flash
LMArena Vision1222—

Multilingual Mistral Large 3 leads

Mistral Large 3: 52.6 (#79), Step 3.5 Flash: 50.7 (#115)

BenchmarkMistral Large 3Step 3.5 Flash
LMArena Non-English14121386
LMArena Chinese14481448
LMArena French14561421
LMArena German14381404
LMArena Japanese13991353
LMArena Korean13841350
LMArena Russian14121385
LMArena Spanish14371419

Instruction Following Too close to call

Mistral Large 3: 74.1 (#104), Step 3.5 Flash: 73.3 (#119)

BenchmarkMistral Large 3Step 3.5 Flash
LMArena Instruction Following14021385

Long Context Too close to call

Mistral Large 3: 43.1 (#102), Step 3.5 Flash: 42.8 (#112)

BenchmarkMistral Large 3Step 3.5 Flash
LMArena Longer Query14131402

Writing & Preference Mistral Large 3 leads

Mistral Large 3: 60.2 (#100), Step 3.5 Flash: 59.0 (#108)

BenchmarkMistral Large 3Step 3.5 Flash
LMArena Text14271403
LMArena Creative Writing13851357
LMArena Multi-Turn14291405
EQ-Bench Creative Writing1412—

Frequently asked questions

Is Mistral Large 3 better than Step 3.5 Flash?

Step 3.5 Flash is the stronger model overall, scoring 41.7 to 38.6 on the Noometry Index.

Which is cheaper, Mistral Large 3 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 Large 3 lists at $0.25 and $0.75.

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

Step 3.5 Flash scores higher on coding benchmarks: 41.7 versus 34.1 in the Noometry coding category.

Which has the bigger context window?

Mistral Large 3 does, with 262K tokens against 256K.

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

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

Related comparisons

Go deeper