Model comparison

Ministral 3B vs Step 3

Step 3 is the stronger model overall, scoring 40.5 to 26.2 on the Noometry Index.

Last verified . 0 shared benchmarks.

Ministral 3B Mistral AI

26.2

Rank #338 Confirmed

Step 3 StepFun

40.5

Rank #149 Confirmed

Summary

  • The widest gap is in knowledge, where Step 3 leads 36.8 to 10.4.

Side by side

Ministral 3B and Step 3 specifications
Ministral 3BStep 3
ProviderMistral AIStepFun
Noometry Index26.240.5
Released2024-10-01—
WeightsOpenOpen
Context window131K—
Max output262K—
Input $ / M tokens$0.10—
Output $ / M tokens$0.10—
Results tracked617

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

Category by category

Coding Not comparable

Ministral 3B: —, Step 3: 40.1 (#147)

Coding benchmarks
BenchmarkMinistral 3BStep 3
LMArena Coding—1367

Reasoning Step 3 leads

Ministral 3B: 18.4 (#282), Step 3: 28.4 (#105)

Reasoning benchmarks
BenchmarkMinistral 3BStep 3
Kagi LLM Benchmark—62.3%
LMArena Hard Prompts—1355
DTBench51.7%—
LMCA5.5%—
Epoch Capabilities Index118.1—

Math Step 3 leads

Ministral 3B: 26.6 (#258), Step 3: 37.6 (#148)

Math benchmarks
BenchmarkMinistral 3BStep 3
LMArena Math—1366
MATH Level 514.4%—

Knowledge Step 3 leads

Ministral 3B: 10.4 (#302), Step 3: 36.8 (#164)

Knowledge benchmarks
BenchmarkMinistral 3BStep 3
GPQA Diamond25.3%—
Vectara Hallucination Rate7.3%—
LMArena Expert—1333

Multimodal Not comparable

Ministral 3B: —, Step 3: 35.5 (#86)

Multimodal benchmarks
BenchmarkMinistral 3BStep 3
LMArena Vision—1177

Multilingual Not comparable

Ministral 3B: —, Step 3: 46.3 (#159)

Multilingual benchmarks
BenchmarkMinistral 3BStep 3
LMArena Non-English—1327
LMArena Chinese—1397
LMArena German—1371
LMArena Korean—1269
LMArena Russian—1331
LMArena Spanish—1371

Instruction Following Not comparable

Ministral 3B: —, Step 3: 70.4 (#164)

Instruction Following benchmarks
BenchmarkMinistral 3BStep 3
LMArena Instruction Following—1332

Long Context Not comparable

Ministral 3B: —, Step 3: 40.3 (#157)

Long Context benchmarks
BenchmarkMinistral 3BStep 3
LMArena Longer Query—1326

Writing & Preference Not comparable

Ministral 3B: —, Step 3: 54.3 (#151)

Writing & Preference benchmarks
BenchmarkMinistral 3BStep 3
LMArena Text—1350
LMArena Creative Writing—1321
LMArena Multi-Turn—1341

Frequently asked questions

Is Ministral 3B better than Step 3?

Step 3 is the stronger model overall, scoring 40.5 to 26.2 on the Noometry Index.

How many benchmarks do Ministral 3B and Step 3 share?

0 benchmarks have published results for both models. Ministral 3B has 6 scored results on Noometry and Step 3 has 17.

Related comparisons

Go deeper