Model comparison

Solar Pro4 vs Step 3

Solar Pro4 is the stronger model overall, scoring 42.1 to 40.5 on the Noometry Index.

Last verified . 15 shared benchmarks.

Solar Pro4 Upstage

42.1

Rank #121 Confirmed

Step 3 StepFun

40.5

Rank #149 Confirmed

Summary

  • They share 15 benchmarks with published results for both. Solar Pro4 scores higher in 7 categories and Step 3 in 1 category; 6 gaps are clear of the uncertainty.
  • Step 3 has downloadable open weights; the other is API-only.

Side by side

Solar Pro4 and Step 3 specifications
Solar Pro4Step 3
ProviderUpstageStepFun
Noometry Index42.140.5
Released2026-08-06—
WeightsProprietaryOpen
Context window524K—
Max output131K—
Input $ / M tokens$0.30—
Output $ / M tokens$1.20—
Results tracked1817

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

Category by category

Coding Too close to call

Solar Pro4: 40.1 (#149), Step 3: 40.1 (#147)

Coding benchmarks
BenchmarkSolar Pro4Step 3
LMArena Coding14371367
LMArena WebDev1371—

Reasoning Too close to call

Solar Pro4: 28.5 (#104), Step 3: 28.4 (#105)

Reasoning benchmarks
BenchmarkSolar Pro4Step 3
LMArena Hard Prompts13991355
Kagi LLM Benchmark—62.3%

Math Solar Pro4 leads

Solar Pro4: 38.8 (#128), Step 3: 37.6 (#148)

Math benchmarks
BenchmarkSolar Pro4Step 3
LMArena Math14161366

Knowledge Solar Pro4 leads

Solar Pro4: 39.8 (#129), Step 3: 36.8 (#164)

Knowledge benchmarks
BenchmarkSolar Pro4Step 3
LMArena Expert14271333

Multimodal Not comparable

Solar Pro4: —, Step 3: 35.5 (#86)

Multimodal benchmarks
BenchmarkSolar Pro4Step 3
LMArena Vision—1177

Multilingual Solar Pro4 leads

Solar Pro4: 48.7 (#139), Step 3: 46.3 (#159)

Multilingual benchmarks
BenchmarkSolar Pro4Step 3
LMArena Non-English13611327
LMArena Chinese14151397
LMArena German13641371
LMArena Korean13821269
LMArena Russian13601331
LMArena Spanish14011371
LMArena French1397—
LMArena Japanese1309—

Instruction Following Solar Pro4 leads

Solar Pro4: 72.7 (#132), Step 3: 70.4 (#164)

Instruction Following benchmarks
BenchmarkSolar Pro4Step 3
LMArena Instruction Following13771332

Long Context Solar Pro4 leads

Solar Pro4: 42.1 (#130), Step 3: 40.3 (#157)

Long Context benchmarks
BenchmarkSolar Pro4Step 3
LMArena Longer Query13811326

Writing & Preference Solar Pro4 leads

Solar Pro4: 56.5 (#138), Step 3: 54.3 (#151)

Writing & Preference benchmarks
BenchmarkSolar Pro4Step 3
LMArena Text13861350
LMArena Creative Writing13161321
LMArena Multi-Turn13851341

Frequently asked questions

Is Solar Pro4 better than Step 3?

Solar Pro4 is the stronger model overall, scoring 42.1 to 40.5 on the Noometry Index.

Is Solar Pro4 or Step 3 better for coding?

They score almost the same on coding (40.1 vs 40.1); test both on your own repository before choosing.

How many benchmarks do Solar Pro4 and Step 3 share?

15 benchmarks have published results for both models. Solar Pro4 has 18 scored results on Noometry and Step 3 has 17.

Related comparisons

Go deeper