Model comparison

Mistral Large 4 vs Step 3.7 Flash

Mistral Large 4 is the stronger model overall, scoring 43.1 to 37.3 on the Noometry Index. Step 3.7 Flash costs 2.5× less per token, which makes it the better buy when Mistral Large 4's lead doesn't matter for your workload.

Last verified . 1 shared benchmarks.

Mistral Large 4 Mistral AI

43.1

Rank #99 Confirmed

Step 3.7 Flash StepFun

37.3

Rank #207 Reported

Summary

  • They share 1 benchmark with published results for both. Mistral Large 4 scores higher in 2 categories and Step 3.7 Flash in 1 category; 2 gaps are clear of the uncertainty.
  • The widest gap is in coding, where Mistral Large 4 leads 48.6 to 40.0.
  • The biggest single-benchmark swing is NYT Connections (extended): 27.4% for Mistral Large 4 and 39.7% for Step 3.7 Flash.
  • Step 3.7 Flash is cheaper at $0.18 / $1.11 per million input/output tokens, against $0.68 / $2.09 for Mistral Large 4.
  • Mistral Large 4 accepts more context: 1.05M tokens versus 256K.
  • Step 3.7 Flash has downloadable open weights; the other is API-only.

Side by side

Mistral Large 4 and Step 3.7 Flash specifications
Mistral Large 4Step 3.7 Flash
ProviderMistral AIStepFun
Noometry Index43.137.3
Released2026-10-062026-05-29
WeightsProprietaryOpen
Context window1.05M256K
Max output262K256K
Input $ / M tokens$0.68$0.18
Output $ / M tokens$2.09$1.11
Results tracked155

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

Category by category

Coding Mistral Large 4 leads

Mistral Large 4: 48.6 (#57), Step 3.7 Flash: 40.0 (#150)

Coding benchmarks
BenchmarkMistral Large 4Step 3.7 Flash
LMArena WebDev1541—
SciCode—40%
LMArena Coding1475—
ALE-Bench—694.12

Reasoning Too close to call

Mistral Large 4: 22.5 (#192), Step 3.7 Flash: 21.6 (#219)

Reasoning benchmarks
BenchmarkMistral Large 4Step 3.7 Flash
NYT Connections (extended)27.4%39.7%
CritPt—2.3%
LMArena Hard Prompts1444—

Math Step 3.7 Flash leads

Mistral Large 4: 40.4 (#91), Step 3.7 Flash: 42.9 (#82)

Math benchmarks
BenchmarkMistral Large 4Step 3.7 Flash
MathArena Final-Answer Competitions—68.5%
LMArena Math1488—

Knowledge Not comparable

Mistral Large 4: 36.6 (#166), Step 3.7 Flash: —

Knowledge benchmarks
BenchmarkMistral Large 4Step 3.7 Flash
SimpleQA Verified20%—
LMArena Expert1447—

Multilingual Not comparable

Mistral Large 4: 52.6 (#82), Step 3.7 Flash: —

Multilingual benchmarks
BenchmarkMistral Large 4Step 3.7 Flash
LMArena Non-English1415—
LMArena Chinese1491—
LMArena Russian1414—

Instruction Following Not comparable

Mistral Large 4: 75.0 (#76), Step 3.7 Flash: —

Instruction Following benchmarks
BenchmarkMistral Large 4Step 3.7 Flash
LMArena Instruction Following1424—

Long Context Not comparable

Mistral Large 4: 43.6 (#89), Step 3.7 Flash: —

Long Context benchmarks
BenchmarkMistral Large 4Step 3.7 Flash
LMArena Longer Query1429—

Writing & Preference Not comparable

Mistral Large 4: 60.4 (#97), Step 3.7 Flash: —

Writing & Preference benchmarks
BenchmarkMistral Large 4Step 3.7 Flash
LMArena Text1427—
LMArena Creative Writing1361—
LMArena Multi-Turn1424—

Frequently asked questions

Is Mistral Large 4 better than Step 3.7 Flash?

Mistral Large 4 is the stronger model overall, scoring 43.1 to 37.3 on the Noometry Index. Step 3.7 Flash costs 2.5× less per token, which makes it the better buy when Mistral Large 4's lead doesn't matter for your workload.

Which is cheaper, Mistral Large 4 or Step 3.7 Flash?

Step 3.7 Flash is cheaper. It lists at $0.18 per million input tokens and $1.11 per million output tokens; Mistral Large 4 lists at $0.68 and $2.09.

Is Mistral Large 4 or Step 3.7 Flash better for coding?

Mistral Large 4 scores higher on coding benchmarks: 48.6 versus 40.0 in the Noometry coding category.

Which has the bigger context window?

Mistral Large 4 does, with 1.05M tokens against 256K.

How many benchmarks do Mistral Large 4 and Step 3.7 Flash share?

1 benchmark has published results for both models. Mistral Large 4 has 15 scored results on Noometry and Step 3.7 Flash has 5.

Related comparisons

Go deeper