Noometry

Model comparison

Gemini 2.5 Flash-Lite vs Step 3

Step 3 is the stronger model overall, scoring 40.5 to 37.0 on the Noometry Index.

Last verified . 17 shared benchmarks.

Gemini 2.5 Flash-Lite Google

37.0

Rank #211 Confirmed

Step 3 StepFun

40.5

Rank #149 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Gemini 2.5 Flash-Lite scores higher in 3 categories and Step 3 in 6 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in long context, where Step 3 leads 40.3 to 33.3.
  • The biggest single-benchmark swing is Kagi LLM Benchmark: 40.5% for Gemini 2.5 Flash-Lite and 62.3% for Step 3.
  • Step 3 has downloadable open weights; the other is API-only.

Side by side

Gemini 2.5 Flash-LiteStep 3
ProviderGoogleStepFun
Noometry Index37.040.5
Released2025-06-17—
WeightsProprietaryOpen
Context window1.05M—
Max output66K—
Input $ / M tokens$0.10—
Output $ / M tokens$0.40—
Results tracked3317

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

Category by category

Coding Step 3 leads

Gemini 2.5 Flash-Lite: 38.5 (#173), Step 3: 40.1 (#147)

BenchmarkGemini 2.5 Flash-LiteStep 3
LMArena Coding13731367
WeirdML35.2%—
ALE-Bench325.9—

Agentic & Tool Use Not comparable

Gemini 2.5 Flash-Lite: 28.0 (#96), Step 3: —

BenchmarkGemini 2.5 Flash-LiteStep 3
Berkeley Function Calling Leaderboard36.9%—

Reasoning Step 3 leads

Gemini 2.5 Flash-Lite: 22.2 (#205), Step 3: 28.4 (#105)

BenchmarkGemini 2.5 Flash-LiteStep 3
Kagi LLM Benchmark40.5%62.3%
LMArena Hard Prompts13771355
DTBench62.8%—
LMCA18.1%—
Epoch Capabilities Index133.94—

Math Too close to call

Gemini 2.5 Flash-Lite: 38.0 (#144), Step 3: 37.6 (#148)

BenchmarkGemini 2.5 Flash-LiteStep 3
LMArena Math13731366
Omni-MATH48%—

Knowledge Step 3 leads

Gemini 2.5 Flash-Lite: 32.5 (#210), Step 3: 36.8 (#164)

BenchmarkGemini 2.5 Flash-LiteStep 3
LMArena Expert13731333
MMLU-Pro53.7%—
Vectara Hallucination Rate3.3%—
GPQA (HELM)30.9%—

Multimodal Step 3 leads

Gemini 2.5 Flash-Lite: 29.1 (#114), Step 3: 35.5 (#86)

BenchmarkGemini 2.5 Flash-LiteStep 3
LMArena Vision11981177
VPCT30%—

Multilingual Gemini 2.5 Flash-Lite leads

Gemini 2.5 Flash-Lite: 49.3 (#134), Step 3: 46.3 (#159)

BenchmarkGemini 2.5 Flash-LiteStep 3
LMArena Non-English13691327
LMArena Chinese14041397
LMArena German13891371
LMArena Korean13601269
LMArena Russian13731331
LMArena Spanish13961371
LMArena French1388—
LMArena Japanese1359—

Instruction Following Too close to call

Gemini 2.5 Flash-Lite: 70.0 (#168), Step 3: 70.4 (#164)

BenchmarkGemini 2.5 Flash-LiteStep 3
LMArena Instruction Following13671332
IFEval81%—

Long Context Step 3 leads

Gemini 2.5 Flash-Lite: 33.3 (#262), Step 3: 40.3 (#157)

BenchmarkGemini 2.5 Flash-LiteStep 3
LMArena Longer Query13731326
Fiction.LiveBench47.2%—

Writing & Preference Gemini 2.5 Flash-Lite leads

Gemini 2.5 Flash-Lite: 56.8 (#135), Step 3: 54.3 (#151)

BenchmarkGemini 2.5 Flash-LiteStep 3
LMArena Text13791350
LMArena Creative Writing13671321
LMArena Multi-Turn13661341
WildBench81.8%—

Frequently asked questions

Is Gemini 2.5 Flash-Lite better than Step 3?

Step 3 is the stronger model overall, scoring 40.5 to 37.0 on the Noometry Index.

Is Gemini 2.5 Flash-Lite or Step 3 better for coding?

Step 3 scores higher on coding benchmarks: 40.1 versus 38.5 in the Noometry coding category.

How many benchmarks do Gemini 2.5 Flash-Lite and Step 3 share?

17 benchmarks have published results for both models. Gemini 2.5 Flash-Lite has 33 scored results on Noometry and Step 3 has 17.

Related comparisons

Go deeper