Noometry

Model comparison

Mistral Medium vs Step 3.7 Flash

Step 3.7 Flash is the stronger model overall, scoring 37.3 to 36.3 on the Noometry Index.

Last verified . 3 shared benchmarks.

Mistral Medium Mistral AI

36.3

Rank #218 Confirmed

Step 3.7 Flash StepFun

37.3

Rank #207 Reported

Summary

  • They share 3 benchmarks with published results for both. Mistral Medium scores higher in 1 category and Step 3.7 Flash in 2 categories; 3 gaps are clear of the uncertainty.
  • The widest gap is in math, where Step 3.7 Flash leads 42.9 to 28.1.
  • Step 3.7 Flash is cheaper at $0.18 / $1.11 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium.
  • Mistral Medium accepts more context: 262K tokens versus 256K.

Side by side

Mistral MediumStep 3.7 Flash
ProviderMistral AIStepFun
Noometry Index36.337.3
Released2023-12-112026-05-29
WeightsOpenOpen
Context window262K256K
Max output262K256K
Input $ / M tokens$1.50$0.18
Output $ / M tokens$7.50$1.11
Results tracked365

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

Category by category

Coding Step 3.7 Flash leads

Mistral Medium: 34.2 (#243), Step 3.7 Flash: 40.0 (#150)

BenchmarkMistral MediumStep 3.7 Flash
SciCode40.2%40%
ALE-Bench763.98694.12
FrontierCode8%—
WeirdML43.7%—
LMArena Coding1434—

Agentic & Tool Use Not comparable

Mistral Medium: 28.3 (#90), Step 3.7 Flash: —

BenchmarkMistral MediumStep 3.7 Flash
Berkeley Function Calling Leaderboard37.7%—

Reasoning Mistral Medium leads

Mistral Medium: 24.0 (#167), Step 3.7 Flash: 21.6 (#219)

BenchmarkMistral MediumStep 3.7 Flash
CritPt0%2.3%
Kagi LLM Benchmark50%—
NYT Connections (extended)—39.7%
LMArena Hard Prompts1426—
DTBench75.5%—
LMCA26.1%—
Surface Evolver Bench26.9%—

Math Step 3.7 Flash leads

Mistral Medium: 28.1 (#245), Step 3.7 Flash: 42.9 (#82)

BenchmarkMistral MediumStep 3.7 Flash
MathArena Final-Answer Competitions—68.5%
OTIS Mock AIME 2024-202532.2%—
ProofBench9%—
LMArena Math1408—
MATH Level 581.6%—
FrontierMath (Feb 2025 set)0.3%—

Knowledge Not comparable

Mistral Medium: 25.0 (#265), Step 3.7 Flash: —

BenchmarkMistral MediumStep 3.7 Flash
GPQA Diamond59.5%—
Humanity's Last Exam4.5%—
Vectara Hallucination Rate22.7%—
LMArena Expert1408—

Multimodal Not comparable

Mistral Medium: 35.3 (#88), Step 3.7 Flash: —

BenchmarkMistral MediumStep 3.7 Flash
LMArena Vision1172—

Multilingual Not comparable

Mistral Medium: 52.1 (#91), Step 3.7 Flash: —

BenchmarkMistral MediumStep 3.7 Flash
LMArena Non-English1408—
LMArena Chinese1447—
LMArena French1459—
LMArena German1432—
LMArena Japanese1378—
LMArena Korean1380—
LMArena Russian1411—
LMArena Spanish1433—

Instruction Following Not comparable

Mistral Medium: 73.7 (#116), Step 3.7 Flash: —

BenchmarkMistral MediumStep 3.7 Flash
LMArena Instruction Following1398—

Long Context Not comparable

Mistral Medium: 42.9 (#114), Step 3.7 Flash: —

BenchmarkMistral MediumStep 3.7 Flash
LMArena Longer Query1406—

Writing & Preference Not comparable

Mistral Medium: 60.0 (#103), Step 3.7 Flash: —

BenchmarkMistral MediumStep 3.7 Flash
LMArena Text1424—
LMArena Creative Writing1391—
Short-Story Creative Writing77.3%—
LMArena Multi-Turn1418—

Frequently asked questions

Is Mistral Medium better than Step 3.7 Flash?

Step 3.7 Flash is the stronger model overall, scoring 37.3 to 36.3 on the Noometry Index.

Which is cheaper, Mistral Medium 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 Medium lists at $1.50 and $7.50.

Is Mistral Medium or Step 3.7 Flash better for coding?

Step 3.7 Flash scores higher on coding benchmarks: 40.0 versus 34.2 in the Noometry coding category.

Which has the bigger context window?

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

How many benchmarks do Mistral Medium and Step 3.7 Flash share?

3 benchmarks have published results for both models. Mistral Medium has 36 scored results on Noometry and Step 3.7 Flash has 5.

Related comparisons

Go deeper