Model comparison

C4ai Aya Expanse 32b vs Step 3.5 Flash

Step 3.5 Flash is the stronger model overall, scoring 41.7 to 35.3 on the Noometry Index.

Last verified . 17 shared benchmarks.

C4ai Aya Expanse 32b Cohere

35.3

Rank #216 Confirmed

Step 3.5 Flash StepFun

41.7

Rank #116 Confirmed

Summary

  • They share 17 benchmarks with published results for both. C4ai Aya Expanse 32b scores higher in 1 category and Step 3.5 Flash in 7 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Step 3.5 Flash leads 59.0 to 42.4.
  • Step 3.5 Flash accepts more context: 256K tokens versus 128K.

Side by side

C4ai Aya Expanse 32b and Step 3.5 Flash specifications
C4ai Aya Expanse 32bStep 3.5 Flash
ProviderCohereStepFun
Noometry Index35.341.7
Released2024-10-242026-01-29
WeightsOpenOpen
Context window128K256K
Max output4K256K
Input $ / M tokens—$0.10
Output $ / M tokens—$0.30
Results tracked1819

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

Category by category

Coding Step 3.5 Flash leads

C4ai Aya Expanse 32b: 34.3 (#227), Step 3.5 Flash: 41.7 (#106)

Coding benchmarks
BenchmarkC4ai Aya Expanse 32bStep 3.5 Flash
LMArena Coding11971436

Reasoning C4ai Aya Expanse 32b leads

C4ai Aya Expanse 32b: 22.3 (#183), Step 3.5 Flash: 21.2 (#202)

Reasoning benchmarks
BenchmarkC4ai Aya Expanse 32bStep 3.5 Flash
LMArena Hard Prompts11931411
NYT Connections (extended)—28.4%

Math Step 3.5 Flash leads

C4ai Aya Expanse 32b: 31.4 (#195), Step 3.5 Flash: 40.6 (#77)

Math benchmarks
BenchmarkC4ai Aya Expanse 32bStep 3.5 Flash
LMArena Math12001408
MathArena Final-Answer Competitions—66.8%

Knowledge Step 3.5 Flash leads

C4ai Aya Expanse 32b: 32.6 (#202), Step 3.5 Flash: 39.0 (#127)

Knowledge benchmarks
BenchmarkC4ai Aya Expanse 32bStep 3.5 Flash
LMArena Expert11821422
Vectara Hallucination Rate10.9%—

Multilingual Step 3.5 Flash leads

C4ai Aya Expanse 32b: 38.5 (#225), Step 3.5 Flash: 50.7 (#115)

Multilingual benchmarks
BenchmarkC4ai Aya Expanse 32bStep 3.5 Flash
LMArena Non-English12131386
LMArena Chinese12101448
LMArena French12471421
LMArena German11991404
LMArena Japanese11631353
LMArena Korean11581350
LMArena Russian12271385
LMArena Spanish11931419

Instruction Following Step 3.5 Flash leads

C4ai Aya Expanse 32b: 62.9 (#232), Step 3.5 Flash: 73.3 (#119)

Instruction Following benchmarks
BenchmarkC4ai Aya Expanse 32bStep 3.5 Flash
LMArena Instruction Following11961385

Long Context Step 3.5 Flash leads

C4ai Aya Expanse 32b: 37.2 (#215), Step 3.5 Flash: 42.8 (#112)

Long Context benchmarks
BenchmarkC4ai Aya Expanse 32bStep 3.5 Flash
LMArena Longer Query12281402

Writing & Preference Step 3.5 Flash leads

C4ai Aya Expanse 32b: 42.4 (#230), Step 3.5 Flash: 59.0 (#108)

Writing & Preference benchmarks
BenchmarkC4ai Aya Expanse 32bStep 3.5 Flash
LMArena Text12241403
LMArena Creative Writing12001357
LMArena Multi-Turn11901405

Frequently asked questions

Is C4ai Aya Expanse 32b better than Step 3.5 Flash?

Step 3.5 Flash is the stronger model overall, scoring 41.7 to 35.3 on the Noometry Index.

Is C4ai Aya Expanse 32b or Step 3.5 Flash better for coding?

Step 3.5 Flash scores higher on coding benchmarks: 41.7 versus 34.3 in the Noometry coding category.

Which has the bigger context window?

Step 3.5 Flash does, with 256K tokens against 128K.

How many benchmarks do C4ai Aya Expanse 32b and Step 3.5 Flash share?

17 benchmarks have published results for both models. C4ai Aya Expanse 32b has 18 scored results on Noometry and Step 3.5 Flash has 19.

Related comparisons

Go deeper