Noometry

Model comparison

Gemini 2.5 Flash-Lite vs Step 3

Step 3 is the stronger model overall, scoring 39.9 to 36.4 on the Noometry Index.

Last verified . 17 shared benchmarks.

Gemini 2.5 Flash-Lite Google

36.4

Rank #208 Confirmed

Step 3 StepFun

39.9

Rank #145 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 Index36.439.9
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: 38.0 (#167), Step 3: 39.5 (#144)

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

Agentic & Tool Use Not comparable

Gemini 2.5 Flash-Lite: 27.8 (#89), Step 3: —

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

Reasoning Step 3 leads

Gemini 2.5 Flash-Lite: 21.5 (#196), Step 3: 27.6 (#102)

BenchmarkGemini 2.5 Flash-LiteStep 3
Kagi LLM Benchmark40.5%62.3%
LMArena Hard Prompts13771355
DTBench62.8%—
LMCA18.1%—
Epoch Capabilities Index133.93—

Math Too close to call

Gemini 2.5 Flash-Lite: 35.5 (#144), Step 3: 34.9 (#148)

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

Knowledge Step 3 leads

Gemini 2.5 Flash-Lite: 32.1 (#206), Step 3: 36.2 (#161)

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: 28.6 (#109), Step 3: 34.9 (#81)

BenchmarkGemini 2.5 Flash-LiteStep 3
LMArena Vision11981176
VPCT30%—

Multilingual Gemini 2.5 Flash-Lite leads

Gemini 2.5 Flash-Lite: 49.5 (#129), Step 3: 46.5 (#154)

BenchmarkGemini 2.5 Flash-LiteStep 3
LMArena Non-English13691327
LMArena Chinese14041396
LMArena German13901371
LMArena Korean13581271
LMArena Russian13731331
LMArena Spanish13961372
LMArena French1388—
LMArena Japanese1359—

Instruction Following Too close to call

Gemini 2.5 Flash-Lite: 70.2 (#163), Step 3: 70.6 (#159)

BenchmarkGemini 2.5 Flash-LiteStep 3
LMArena Instruction Following13661332
IFEval81%—

Long Context Step 3 leads

Gemini 2.5 Flash-Lite: 33.3 (#257), Step 3: 40.3 (#152)

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: 57.0 (#130), Step 3: 54.5 (#146)

BenchmarkGemini 2.5 Flash-LiteStep 3
LMArena Text13791351
LMArena Creative Writing13661322
LMArena Multi-Turn13671340
WildBench81.8%—

Frequently asked questions

Is Gemini 2.5 Flash-Lite better than Step 3?

Step 3 is the stronger model overall, scoring 39.9 to 36.4 on the Noometry Index.

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

Step 3 scores higher on coding benchmarks: 39.5 versus 38.0 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