Model comparison

Mistral Nemo vs Step 5 Preview

Step 5 Preview is the stronger model overall, scoring 47.9 to 26.4 on the Noometry Index. Mistral Nemo costs 9.5× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.

Last verified . 0 shared benchmarks.

Mistral Nemo Mistral AI

26.4

Rank #337 Confirmed

Step 5 Preview StepFun

47.9

Rank #58 Confirmed

Summary

  • The widest gap is in writing & preference, where Step 5 Preview leads 62.8 to 28.5.
  • Mistral Nemo is cheaper at $0.15 / $0.15 per million input/output tokens, against $1 / $2.70 for Step 5 Preview.
  • Step 5 Preview accepts more context: 1.02M tokens versus 128K.
  • Mistral Nemo has downloadable open weights; the other is API-only.

Side by side

Mistral Nemo and Step 5 Preview specifications
Mistral NemoStep 5 Preview
ProviderMistral AIStepFun
Noometry Index26.447.9
Released2024-07-012026-09-16
WeightsOpenProprietary
Context window128K1.02M
Max output128K66K
Input $ / M tokens$0.15$1
Output $ / M tokens$0.15$2.70
Results tracked1018

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

Category by category

Coding Not comparable

Mistral Nemo: —, Step 5 Preview: 51.8 (#36)

Coding benchmarks
BenchmarkMistral NemoStep 5 Preview
LMArena WebDev—1564
SciCode—58.9%
LMArena Coding—1480

Agentic & Tool Use Not comparable

Mistral Nemo: 23.5 (#125), Step 5 Preview: —

Agentic & Tool Use benchmarks
BenchmarkMistral NemoStep 5 Preview
Berkeley Function Calling Leaderboard27.6%—
BALROG17.6%—

Reasoning Step 5 Preview leads

Mistral Nemo: 20.7 (#232), Step 5 Preview: 40.0 (#57)

Reasoning benchmarks
BenchmarkMistral NemoStep 5 Preview
CritPt—20.9%
LMArena Hard Prompts—1465
DTBench48.6%—
Epoch Capabilities Index118.68—
PIQA83.5%—

Math Step 5 Preview leads

Mistral Nemo: 25.5 (#268), Step 5 Preview: 46.1 (#72)

Math benchmarks
BenchmarkMistral NemoStep 5 Preview
ProofBench—42%
LMArena Math—1470
MATH Level 510.8%—
GSM8K84.2%—

Knowledge Step 5 Preview leads

Mistral Nemo: 12.3 (#298), Step 5 Preview: 41.2 (#112)

Knowledge benchmarks
BenchmarkMistral NemoStep 5 Preview
GPQA Diamond29.9%—
LMArena Expert—1470
BoolQ82.5%—

Multimodal Not comparable

Mistral Nemo: —, Step 5 Preview: 41.0 (#41)

Multimodal benchmarks
BenchmarkMistral NemoStep 5 Preview
LMArena Vision—1267

Multilingual Not comparable

Mistral Nemo: —, Step 5 Preview: 53.8 (#54)

Multilingual benchmarks
BenchmarkMistral NemoStep 5 Preview
LMArena Non-English—1432
LMArena Chinese—1519
LMArena Russian—1436
LMArena Spanish—1439

Instruction Following Not comparable

Mistral Nemo: —, Step 5 Preview: 76.0 (#50)

Instruction Following benchmarks
BenchmarkMistral NemoStep 5 Preview
LMArena Instruction Following—1444

Long Context Not comparable

Mistral Nemo: —, Step 5 Preview: 44.5 (#64)

Long Context benchmarks
BenchmarkMistral NemoStep 5 Preview
LMArena Longer Query—1455

Writing & Preference Step 5 Preview leads

Mistral Nemo: 28.5 (#296), Step 5 Preview: 62.8 (#71)

Writing & Preference benchmarks
BenchmarkMistral NemoStep 5 Preview
LMArena Text—1442
LMArena Creative Writing—1410
EQ-Bench Creative Writing881—
LMArena Multi-Turn—1447

Frequently asked questions

Is Mistral Nemo better than Step 5 Preview?

Step 5 Preview is the stronger model overall, scoring 47.9 to 26.4 on the Noometry Index. Mistral Nemo costs 9.5× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.

Which is cheaper, Mistral Nemo or Step 5 Preview?

Mistral Nemo is cheaper. It lists at $0.15 per million input tokens and $0.15 per million output tokens; Step 5 Preview lists at $1 and $2.70.

Which has the bigger context window?

Step 5 Preview does, with 1.02M tokens against 128K.

How many benchmarks do Mistral Nemo and Step 5 Preview share?

0 benchmarks have published results for both models. Mistral Nemo has 10 scored results on Noometry and Step 5 Preview has 18.

Related comparisons

Go deeper