Noometry

Model comparison

Gemini 3.1 Flash Lite vs Step 3

Gemini 3.1 Flash Lite and Step 3 score almost the same on the Noometry Index (40.8 vs 40.5), so choose on price, context window or the category you care about most.

Last verified . 17 shared benchmarks.

Gemini 3.1 Flash Lite Google

40.8

Rank #144 Confirmed

Step 3 StepFun

40.5

Rank #149 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Gemini 3.1 Flash Lite scores higher in 7 categories and Step 3 in 2 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Gemini 3.1 Flash Lite leads 60.9 to 54.3.
  • Step 3 has downloadable open weights; the other is API-only.

Side by side

Gemini 3.1 Flash LiteStep 3
ProviderGoogleStepFun
Noometry Index40.840.5
Released2026-03-03—
WeightsProprietaryOpen
Context window1.05M—
Max output66K—
Input $ / M tokens$0.25—
Output $ / M tokens$1.50—
Results tracked3817

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

Category by category

Coding Step 3 leads

Gemini 3.1 Flash Lite: 37.8 (#188), Step 3: 40.1 (#147)

BenchmarkGemini 3.1 Flash LiteStep 3
LMArena Coding14001367
LMArena WebDev1256—
SciCode41.9%—
WeirdML52.2%—
ALE-Bench797.73—

Agentic & Tool Use Not comparable

Gemini 3.1 Flash Lite: 30.2 (#79), Step 3: —

BenchmarkGemini 3.1 Flash LiteStep 3
DeepResearch Bench37.3%—

Reasoning Step 3 leads

Gemini 3.1 Flash Lite: 22.9 (#186), Step 3: 28.4 (#105)

BenchmarkGemini 3.1 Flash LiteStep 3
Kagi LLM Benchmark67.2%62.3%
LMArena Hard Prompts14071355
NYT Connections (extended)8.2%—
CritPt1.1%—
Chess Puzzles25%—
EnigmaEval3%—
Thematic Generalization63.3%—
DTBench76.8%—
LMCA35%—
Epoch Capabilities Index144.47—
ForecastBench54.4—

Math Gemini 3.1 Flash Lite leads

Gemini 3.1 Flash Lite: 40.7 (#90), Step 3: 37.6 (#148)

BenchmarkGemini 3.1 Flash LiteStep 3
LMArena Math14281366
FrontierMath (Tiers 1-3)27.7%—
OTIS Mock AIME 2024-202580%—

Knowledge Gemini 3.1 Flash Lite leads

Gemini 3.1 Flash Lite: 41.9 (#104), Step 3: 36.8 (#164)

BenchmarkGemini 3.1 Flash LiteStep 3
LMArena Expert13981333
GPQA Diamond81.8%—
Humanity's Last Exam8.6%—
Vectara Hallucination Rate8.2%—

Multimodal Gemini 3.1 Flash Lite leads

Gemini 3.1 Flash Lite: 39.4 (#60), Step 3: 35.5 (#86)

BenchmarkGemini 3.1 Flash LiteStep 3
LMArena Vision12401177

Multilingual Gemini 3.1 Flash Lite leads

Gemini 3.1 Flash Lite: 52.3 (#86), Step 3: 46.3 (#159)

BenchmarkGemini 3.1 Flash LiteStep 3
LMArena Non-English14111327
LMArena Chinese14611397
LMArena German14291371
LMArena Korean13921269
LMArena Russian14201331
LMArena Spanish14211371
LMArena French1424—
LMArena Japanese1413—

Instruction Following Gemini 3.1 Flash Lite leads

Gemini 3.1 Flash Lite: 72.7 (#131), Step 3: 70.4 (#164)

BenchmarkGemini 3.1 Flash LiteStep 3
LMArena Instruction Following13771332

Long Context Gemini 3.1 Flash Lite leads

Gemini 3.1 Flash Lite: 42.5 (#122), Step 3: 40.3 (#157)

BenchmarkGemini 3.1 Flash LiteStep 3
LMArena Longer Query13941326

Writing & Preference Gemini 3.1 Flash Lite leads

Gemini 3.1 Flash Lite: 60.9 (#94), Step 3: 54.3 (#151)

BenchmarkGemini 3.1 Flash LiteStep 3
LMArena Text14161350
LMArena Creative Writing14011321
LMArena Multi-Turn14171341

Frequently asked questions

Is Gemini 3.1 Flash Lite better than Step 3?

Gemini 3.1 Flash Lite and Step 3 score almost the same on the Noometry Index (40.8 vs 40.5), so choose on price, context window or the category you care about most.

Is Gemini 3.1 Flash Lite or Step 3 better for coding?

Step 3 scores higher on coding benchmarks: 40.1 versus 37.8 in the Noometry coding category.

How many benchmarks do Gemini 3.1 Flash Lite and Step 3 share?

17 benchmarks have published results for both models. Gemini 3.1 Flash Lite has 38 scored results on Noometry and Step 3 has 17.

Related comparisons

Go deeper