Model comparison

Gemma 4 26B A4B IT vs Step 5 Preview

Step 5 Preview is the stronger model overall, scoring 47.9 to 43.5 on the Noometry Index. Gemma 4 26B A4B IT costs 13× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.

Last verified . 17 shared benchmarks.

Gemma 4 26B A4B IT Google

43.5

Rank #92 Confirmed

Step 5 Preview StepFun

47.9

Rank #58 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Gemma 4 26B A4B IT scores higher in 2 categories and Step 5 Preview in 7 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Step 5 Preview leads 40.0 to 21.8.
  • The biggest single-benchmark swing is CritPt: 0% for Gemma 4 26B A4B IT and 20.9% for Step 5 Preview.
  • Gemma 4 26B A4B IT is cheaper at $0.0675 / $0.23 per million input/output tokens, against $1 / $2.70 for Step 5 Preview.
  • Step 5 Preview accepts more context: 1.02M tokens versus 262K.
  • Gemma 4 26B A4B IT has downloadable open weights; the other is API-only.

Side by side

Gemma 4 26B A4B IT and Step 5 Preview specifications
Gemma 4 26B A4B ITStep 5 Preview
ProviderGoogleStepFun
Noometry Index43.547.9
Released2026-04-022026-09-16
WeightsOpenProprietary
Context window262K1.02M
Max output33K66K
Input $ / M tokens$0.0675$1
Output $ / M tokens$0.23$2.70
Results tracked2818

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

Category by category

Coding Step 5 Preview leads

Gemma 4 26B A4B IT: 39.0 (#164), Step 5 Preview: 51.8 (#36)

Coding benchmarks
BenchmarkGemma 4 26B A4B ITStep 5 Preview
LMArena WebDev13591564
SciCode40%58.9%
LMArena Coding14471480
WeirdML35.2%—
ALE-Bench927.17—

Reasoning Step 5 Preview leads

Gemma 4 26B A4B IT: 21.8 (#213), Step 5 Preview: 40.0 (#57)

Reasoning benchmarks
BenchmarkGemma 4 26B A4B ITStep 5 Preview
CritPt0%20.9%
LMArena Hard Prompts14391465
Chess Puzzles6%—
DTBench74.9%—
LMCA29.7%—
Epoch Capabilities Index141.85—

Math Gemma 4 26B A4B IT leads

Gemma 4 26B A4B IT: 47.6 (#67), Step 5 Preview: 46.1 (#72)

Math benchmarks
BenchmarkGemma 4 26B A4B ITStep 5 Preview
LMArena Math14701470
OTIS Mock AIME 2024-202582.2%—
ProofBench—42%

Knowledge Gemma 4 26B A4B IT leads

Gemma 4 26B A4B IT: 45.7 (#85), Step 5 Preview: 41.2 (#112)

Knowledge benchmarks
BenchmarkGemma 4 26B A4B ITStep 5 Preview
LMArena Expert14471470
GPQA Diamond73.2%—
Vectara Hallucination Rate5.2%—

Multimodal Too close to call

Gemma 4 26B A4B IT: 40.6 (#46), Step 5 Preview: 41.0 (#41)

Multimodal benchmarks
BenchmarkGemma 4 26B A4B ITStep 5 Preview
LMArena Vision12601267

Multilingual Too close to call

Gemma 4 26B A4B IT: 53.1 (#71), Step 5 Preview: 53.8 (#54)

Multilingual benchmarks
BenchmarkGemma 4 26B A4B ITStep 5 Preview
LMArena Non-English14211432
LMArena Chinese14951519
LMArena Russian14341436
LMArena Spanish14171439
LMArena French1460—

Instruction Following Step 5 Preview leads

Gemma 4 26B A4B IT: 74.8 (#82), Step 5 Preview: 76.0 (#50)

Instruction Following benchmarks
BenchmarkGemma 4 26B A4B ITStep 5 Preview
LMArena Instruction Following14201444

Long Context Too close to call

Gemma 4 26B A4B IT: 43.6 (#91), Step 5 Preview: 44.5 (#64)

Long Context benchmarks
BenchmarkGemma 4 26B A4B ITStep 5 Preview
LMArena Longer Query14281455

Writing & Preference Step 5 Preview leads

Gemma 4 26B A4B IT: 58.6 (#115), Step 5 Preview: 62.8 (#71)

Writing & Preference benchmarks
BenchmarkGemma 4 26B A4B ITStep 5 Preview
LMArena Text14341442
LMArena Creative Writing14021410
LMArena Multi-Turn14411447
EQ-Bench Creative Writing1305—

Frequently asked questions

Is Gemma 4 26B A4B IT better than Step 5 Preview?

Step 5 Preview is the stronger model overall, scoring 47.9 to 43.5 on the Noometry Index. Gemma 4 26B A4B IT costs 13× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.

Which is cheaper, Gemma 4 26B A4B IT or Step 5 Preview?

Gemma 4 26B A4B IT is cheaper. It lists at $0.0675 per million input tokens and $0.23 per million output tokens; Step 5 Preview lists at $1 and $2.70.

Is Gemma 4 26B A4B IT or Step 5 Preview better for coding?

Step 5 Preview scores higher on coding benchmarks: 51.8 versus 39.0 in the Noometry coding category.

Which has the bigger context window?

Step 5 Preview does, with 1.02M tokens against 262K.

How many benchmarks do Gemma 4 26B A4B IT and Step 5 Preview share?

17 benchmarks have published results for both models. Gemma 4 26B A4B IT has 28 scored results on Noometry and Step 5 Preview has 18.

Related comparisons

Go deeper