Model comparison

Step 1o Turbo 202506 vs Step 3

Step 1o Turbo 202506 and Step 3 score almost the same on the Noometry Index (39.1 vs 39.9), so choose on price, context window or the category you care about most.

Last verified . 14 shared benchmarks.

Step 1o Turbo 202506 StepFun

39.1

Rank #160 Confirmed

Step 3 StepFun

39.9

Rank #145 Confirmed

Summary

  • They share 14 benchmarks with published results for both. Step 1o Turbo 202506 scores higher in 2 categories and Step 3 in 7 categories; 5 gaps are clear of the uncertainty.
  • Step 3 has downloadable open weights; the other is API-only.

Side by side

Step 1o Turbo 202506 and Step 3 specifications
Step 1o Turbo 202506Step 3
ProviderStepFunStepFun
Noometry Index39.139.9
Released——
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked1417

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

Category by category

Coding Too close to call

Step 1o Turbo 202506: 38.6 (#158), Step 3: 39.5 (#144)

Coding benchmarks
BenchmarkStep 1o Turbo 202506Step 3
LMArena Coding13391367

Reasoning Step 3 leads

Step 1o Turbo 202506: 25.7 (#127), Step 3: 27.6 (#102)

Reasoning benchmarks
BenchmarkStep 1o Turbo 202506Step 3
LMArena Hard Prompts13361355
Kagi LLM Benchmark—62.3%

Math Step 3 leads

Step 1o Turbo 202506: 33.9 (#163), Step 3: 34.9 (#148)

Math benchmarks
BenchmarkStep 1o Turbo 202506Step 3
LMArena Math13181366

Knowledge Too close to call

Step 1o Turbo 202506: 35.5 (#174), Step 3: 36.2 (#161)

Knowledge benchmarks
BenchmarkStep 1o Turbo 202506Step 3
LMArena Expert13081333

Multimodal Too close to call

Step 1o Turbo 202506: 35.4 (#75), Step 3: 34.9 (#81)

Multimodal benchmarks
BenchmarkStep 1o Turbo 202506Step 3
LMArena Vision11861176

Multilingual Step 3 leads

Step 1o Turbo 202506: 45.5 (#168), Step 3: 46.5 (#154)

Multilingual benchmarks
BenchmarkStep 1o Turbo 202506Step 3
LMArena Non-English13131327
LMArena Chinese13801396
LMArena German13151371
LMArena Russian13271331
LMArena Korean—1271
LMArena Spanish—1372

Instruction Following Step 3 leads

Step 1o Turbo 202506: 69.4 (#171), Step 3: 70.6 (#159)

Instruction Following benchmarks
BenchmarkStep 1o Turbo 202506Step 3
LMArena Instruction Following13111332

Long Context Too close to call

Step 1o Turbo 202506: 41.1 (#141), Step 3: 40.3 (#152)

Long Context benchmarks
BenchmarkStep 1o Turbo 202506Step 3
LMArena Longer Query13501326

Writing & Preference Step 3 leads

Step 1o Turbo 202506: 53.4 (#154), Step 3: 54.5 (#146)

Writing & Preference benchmarks
BenchmarkStep 1o Turbo 202506Step 3
LMArena Text13361351
LMArena Creative Writing13081322
LMArena Multi-Turn13411340

Frequently asked questions

Is Step 1o Turbo 202506 better than Step 3?

Step 1o Turbo 202506 and Step 3 score almost the same on the Noometry Index (39.1 vs 39.9), so choose on price, context window or the category you care about most.

Is Step 1o Turbo 202506 or Step 3 better for coding?

They score almost the same on coding (38.6 vs 39.5); test both on your own repository before choosing.

How many benchmarks do Step 1o Turbo 202506 and Step 3 share?

14 benchmarks have published results for both models. Step 1o Turbo 202506 has 14 scored results on Noometry and Step 3 has 17.

Related comparisons

Go deeper