Noometry

Model comparison

Mistral Small vs Step 3.7 Flash

Step 3.7 Flash is the stronger model overall, scoring 37.3 to 33.4 on the Noometry Index. Mistral Small costs 1.6× less per token, which makes it the better buy when Step 3.7 Flash's lead doesn't matter for your workload.

Last verified . 3 shared benchmarks.

Mistral Small Mistral AI

33.4

Rank #243 Confirmed

Step 3.7 Flash StepFun

37.3

Rank #207 Reported

Summary

  • They share 3 benchmarks with published results for both. Mistral Small scores higher in 0 categories and Step 3.7 Flash in 3 categories; 3 gaps are clear of the uncertainty.
  • The widest gap is in math, where Step 3.7 Flash leads 42.9 to 16.4.
  • The biggest single-benchmark swing is SciCode: 26.5% for Mistral Small and 40% for Step 3.7 Flash.
  • Mistral Small is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.18 / $1.11 for Step 3.7 Flash.
  • Mistral Small accepts more context: 262K tokens versus 256K.

Side by side

Mistral SmallStep 3.7 Flash
ProviderMistral AIStepFun
Noometry Index33.437.3
Released2024-02-262026-05-29
WeightsOpenOpen
Context window262K256K
Max output256K256K
Input $ / M tokens$0.15$0.18
Output $ / M tokens$0.60$1.11
Results tracked395

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

Category by category

Coding Step 3.7 Flash leads

Mistral Small: 34.0 (#247), Step 3.7 Flash: 40.0 (#150)

BenchmarkMistral SmallStep 3.7 Flash
SciCode26.5%40%
ALE-Bench497.62694.12
BigCodeBench Instruct36.1%—
LiveBench Coding36.2%—
LMArena Coding1362—
BigCodeBench Complete46.6%—

Agentic & Tool Use Not comparable

Mistral Small: 28.1 (#93), Step 3.7 Flash: —

BenchmarkMistral SmallStep 3.7 Flash
Berkeley Function Calling Leaderboard37.1%—

Reasoning Step 3.7 Flash leads

Mistral Small: 19.8 (#250), Step 3.7 Flash: 21.6 (#219)

BenchmarkMistral SmallStep 3.7 Flash
CritPt0%2.3%
Kagi LLM Benchmark37.8%—
NYT Connections (extended)—39.7%
LiveBench Reasoning44.8%—
LMArena Hard Prompts1335—
DTBench70.9%—
LiveBench Data Analysis53.7%—
LMCA20.6%—
LiveBench44%—

Math Step 3.7 Flash leads

Mistral Small: 16.4 (#293), Step 3.7 Flash: 42.9 (#82)

BenchmarkMistral SmallStep 3.7 Flash
MathArena Final-Answer Competitions—68.5%
OTIS Mock AIME 2024-20255.8%—
LiveBench Math39.9%—
LMArena Math1341—
MATH Level 546.8%—

Knowledge Not comparable

Mistral Small: 31.0 (#222), Step 3.7 Flash: —

BenchmarkMistral SmallStep 3.7 Flash
GPQA Diamond47.5%—
Vectara Hallucination Rate5.1%—
LMArena Expert1291—
MMLU68.7%—

Multimodal Not comparable

Mistral Small: 33.5 (#96), Step 3.7 Flash: —

BenchmarkMistral SmallStep 3.7 Flash
LMArena Vision1142—

Multilingual Not comparable

Mistral Small: 45.5 (#169), Step 3.7 Flash: —

BenchmarkMistral SmallStep 3.7 Flash
LMArena Non-English1315—
LMArena Chinese1340—
LMArena French1337—
LMArena German1340—
LMArena Japanese1275—
LMArena Korean1259—
LMArena Russian1324—
LMArena Spanish1346—

Instruction Following Not comparable

Mistral Small: 66.4 (#209), Step 3.7 Flash: —

BenchmarkMistral SmallStep 3.7 Flash
LiveBench Instruction Following63.7%—
LMArena Instruction Following1310—

Long Context Not comparable

Mistral Small: 40.4 (#156), Step 3.7 Flash: —

BenchmarkMistral SmallStep 3.7 Flash
LMArena Longer Query1327—

Writing & Preference Not comparable

Mistral Small: 52.5 (#171), Step 3.7 Flash: —

BenchmarkMistral SmallStep 3.7 Flash
LMArena Text1338—
LMArena Creative Writing1305—
LMArena Multi-Turn1344—
LiveBench Language30.5%—

Frequently asked questions

Is Mistral Small better than Step 3.7 Flash?

Step 3.7 Flash is the stronger model overall, scoring 37.3 to 33.4 on the Noometry Index. Mistral Small costs 1.6× less per token, which makes it the better buy when Step 3.7 Flash's lead doesn't matter for your workload.

Which is cheaper, Mistral Small or Step 3.7 Flash?

Mistral Small is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Step 3.7 Flash lists at $0.18 and $1.11.

Is Mistral Small or Step 3.7 Flash better for coding?

Step 3.7 Flash scores higher on coding benchmarks: 40.0 versus 34.0 in the Noometry coding category.

Which has the bigger context window?

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

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

3 benchmarks have published results for both models. Mistral Small has 39 scored results on Noometry and Step 3.7 Flash has 5.

Related comparisons

Go deeper