Model comparison

Nova Premier 1.0 vs Step 3.5 Flash

Step 3.5 Flash is the stronger model overall, scoring 42.3 to 38.3 on the Noometry Index.

Last verified . 0 shared benchmarks.

Nova Premier 1.0 Amazon

38.3

Rank #189 Confirmed

Step 3.5 Flash StepFun

42.3

Rank #116 Confirmed

Summary

  • The widest gap is in math, where Step 3.5 Flash leads 42.6 to 33.8.
  • Step 3.5 Flash is cheaper at $0.10 / $0.30 per million input/output tokens, against $2.50 / $12.50 for Nova Premier 1.0.
  • Nova Premier 1.0 accepts more context: 1M tokens versus 256K.
  • Step 3.5 Flash has downloadable open weights; the other is API-only.

Side by side

Nova Premier 1.0 and Step 3.5 Flash specifications
Nova Premier 1.0Step 3.5 Flash
ProviderAmazonStepFun
Noometry Index38.342.3
Released2025-04-302026-01-29
WeightsProprietaryOpen
Context window1M256K
Max output10K256K
Input $ / M tokens$2.50$0.10
Output $ / M tokens$12.50$0.30
Results tracked619

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

Category by category

Coding Not comparable

Nova Premier 1.0: —, Step 3.5 Flash: 42.4 (#105)

Coding benchmarks
BenchmarkNova Premier 1.0Step 3.5 Flash
LMArena Coding—1436

Reasoning Too close to call

Nova Premier 1.0: 23.0 (#185), Step 3.5 Flash: 22.2 (#202)

Reasoning benchmarks
BenchmarkNova Premier 1.0Step 3.5 Flash
Kagi LLM Benchmark44.8%—
NYT Connections (extended)—28.4%
LMArena Hard Prompts—1411

Math Step 3.5 Flash leads

Nova Premier 1.0: 33.8 (#199), Step 3.5 Flash: 42.6 (#84)

Math benchmarks
BenchmarkNova Premier 1.0Step 3.5 Flash
MathArena Final-Answer Competitions—66.8%
Omni-MATH35%—
LMArena Math—1408

Knowledge Step 3.5 Flash leads

Nova Premier 1.0: 35.8 (#180), Step 3.5 Flash: 39.6 (#132)

Knowledge benchmarks
BenchmarkNova Premier 1.0Step 3.5 Flash
MMLU-Pro72.6%—
GPQA (HELM)51.8%—
LMArena Expert—1421

Multilingual Not comparable

Nova Premier 1.0: —, Step 3.5 Flash: 50.5 (#119)

Multilingual benchmarks
BenchmarkNova Premier 1.0Step 3.5 Flash
LMArena Non-English—1385
LMArena Chinese—1447
LMArena French—1421
LMArena German—1405
LMArena Japanese—1354
LMArena Korean—1352
LMArena Russian—1385
LMArena Spanish—1419

Instruction Following Step 3.5 Flash leads

Nova Premier 1.0: 66.8 (#204), Step 3.5 Flash: 73.1 (#124)

Instruction Following benchmarks
BenchmarkNova Premier 1.0Step 3.5 Flash
IFEval80.3%—
LMArena Instruction Following—1385

Long Context Not comparable

Nova Premier 1.0: —, Step 3.5 Flash: 42.8 (#117)

Long Context benchmarks
BenchmarkNova Premier 1.0Step 3.5 Flash
LMArena Longer Query—1402

Writing & Preference Step 3.5 Flash leads

Nova Premier 1.0: 51.0 (#178), Step 3.5 Flash: 58.8 (#113)

Writing & Preference benchmarks
BenchmarkNova Premier 1.0Step 3.5 Flash
LMArena Text—1403
LMArena Creative Writing—1357
WildBench78.8%—
LMArena Multi-Turn—1405

Frequently asked questions

Is Nova Premier 1.0 better than Step 3.5 Flash?

Step 3.5 Flash is the stronger model overall, scoring 42.3 to 38.3 on the Noometry Index.

Which is cheaper, Nova Premier 1.0 or Step 3.5 Flash?

Step 3.5 Flash is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Nova Premier 1.0 lists at $2.50 and $12.50.

Which has the bigger context window?

Nova Premier 1.0 does, with 1M tokens against 256K.

How many benchmarks do Nova Premier 1.0 and Step 3.5 Flash share?

0 benchmarks have published results for both models. Nova Premier 1.0 has 6 scored results on Noometry and Step 3.5 Flash has 19.

Related comparisons

Go deeper