Model comparison

Gemini 2.0 Flash-Lite vs Step 3.5 Flash

Step 3.5 Flash is the stronger model overall, scoring 41.7 to 37.3 on the Noometry Index.

Last verified . 17 shared benchmarks.

Gemini 2.0 Flash-Lite Google

37.3

Rank #189 Confirmed

Step 3.5 Flash StepFun

41.7

Rank #116 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Gemini 2.0 Flash-Lite scores higher in 0 categories and Step 3.5 Flash in 8 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where Step 3.5 Flash leads 40.6 to 31.8.
  • Step 3.5 Flash has downloadable open weights; the other is API-only.

Side by side

Gemini 2.0 Flash-Lite and Step 3.5 Flash specifications
Gemini 2.0 Flash-LiteStep 3.5 Flash
ProviderGoogleStepFun
Noometry Index37.341.7
Released2025-02-052026-01-29
WeightsProprietaryOpen
Context window—256K
Max output—256K
Input $ / M tokens—$0.10
Output $ / M tokens—$0.30
Results tracked3219

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

Category by category

Coding Step 3.5 Flash leads

Gemini 2.0 Flash-Lite: 37.4 (#181), Step 3.5 Flash: 41.7 (#106)

Coding benchmarks
BenchmarkGemini 2.0 Flash-LiteStep 3.5 Flash
LMArena Coding13221436
LiveBench Coding47.1%—

Reasoning Too close to call

Gemini 2.0 Flash-Lite: 21.2 (#203), Step 3.5 Flash: 21.2 (#202)

Reasoning benchmarks
BenchmarkGemini 2.0 Flash-LiteStep 3.5 Flash
LMArena Hard Prompts13241411
NYT Connections (extended)—28.4%
LiveBench Reasoning50.1%—
DTBench52.5%—
LiveBench Data Analysis65.5%—
ForecastBench57.1—
LiveBench54.3%—

Math Step 3.5 Flash leads

Gemini 2.0 Flash-Lite: 31.8 (#192), Step 3.5 Flash: 40.6 (#77)

Math benchmarks
BenchmarkGemini 2.0 Flash-LiteStep 3.5 Flash
LMArena Math13091408
MathArena Final-Answer Competitions—66.8%
Omni-MATH37.4%—
LiveBench Math58.1%—

Knowledge Step 3.5 Flash leads

Gemini 2.0 Flash-Lite: 34.6 (#185), Step 3.5 Flash: 39.0 (#127)

Knowledge benchmarks
BenchmarkGemini 2.0 Flash-LiteStep 3.5 Flash
LMArena Expert13051422
MMLU-Pro72%—
GPQA (HELM)50%—

Multimodal Not comparable

Gemini 2.0 Flash-Lite: 30.6 (#103), Step 3.5 Flash: —

Multimodal benchmarks
BenchmarkGemini 2.0 Flash-LiteStep 3.5 Flash
LMArena Vision1100—

Multilingual Step 3.5 Flash leads

Gemini 2.0 Flash-Lite: 46.2 (#156), Step 3.5 Flash: 50.7 (#115)

Multilingual benchmarks
BenchmarkGemini 2.0 Flash-LiteStep 3.5 Flash
LMArena Non-English13231386
LMArena Chinese13391448
LMArena French13461421
LMArena German13061404
LMArena Japanese13021353
LMArena Korean13251350
LMArena Russian13281385
LMArena Spanish13131419

Instruction Following Step 3.5 Flash leads

Gemini 2.0 Flash-Lite: 70.6 (#158), Step 3.5 Flash: 73.3 (#119)

Instruction Following benchmarks
BenchmarkGemini 2.0 Flash-LiteStep 3.5 Flash
LMArena Instruction Following13051385
LiveBench Instruction Following78.3%—
IFEval82.4%—

Long Context Step 3.5 Flash leads

Gemini 2.0 Flash-Lite: 40.1 (#155), Step 3.5 Flash: 42.8 (#112)

Long Context benchmarks
BenchmarkGemini 2.0 Flash-LiteStep 3.5 Flash
LMArena Longer Query13211402

Writing & Preference Step 3.5 Flash leads

Gemini 2.0 Flash-Lite: 51.9 (#172), Step 3.5 Flash: 59.0 (#108)

Writing & Preference benchmarks
BenchmarkGemini 2.0 Flash-LiteStep 3.5 Flash
LMArena Text13301403
LMArena Creative Writing13191357
LMArena Multi-Turn13071405
WildBench79%—
LiveBench Language34.3%—

Frequently asked questions

Is Gemini 2.0 Flash-Lite better than Step 3.5 Flash?

Step 3.5 Flash is the stronger model overall, scoring 41.7 to 37.3 on the Noometry Index.

Is Gemini 2.0 Flash-Lite or Step 3.5 Flash better for coding?

Step 3.5 Flash scores higher on coding benchmarks: 41.7 versus 37.4 in the Noometry coding category.

How many benchmarks do Gemini 2.0 Flash-Lite and Step 3.5 Flash share?

17 benchmarks have published results for both models. Gemini 2.0 Flash-Lite has 32 scored results on Noometry and Step 3.5 Flash has 19.

Related comparisons

Go deeper