Noometry

Model comparison

Gemini 2.5 Flash vs Step 3

Step 3 is the stronger model overall, scoring 40.5 to 39.3 on the Noometry Index.

Last verified . 17 shared benchmarks.

Gemini 2.5 Flash Google

39.3

Rank #170 Confirmed

Step 3 StepFun

40.5

Rank #149 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Gemini 2.5 Flash scores higher in 5 categories and Step 3 in 4 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Step 3 leads 28.4 to 18.1.
  • The biggest single-benchmark swing is Kagi LLM Benchmark: 56.8% for Gemini 2.5 Flash and 62.3% for Step 3.
  • Step 3 has downloadable open weights; the other is API-only.

Side by side

Gemini 2.5 FlashStep 3
ProviderGoogleStepFun
Noometry Index39.340.5
Released2025-04-17—
WeightsProprietaryOpen
Context window1.05M—
Max output66K—
Input $ / M tokens$0.30—
Output $ / M tokens$2.50—
Results tracked5417

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

Category by category

Coding Step 3 leads

Gemini 2.5 Flash: 35.8 (#220), Step 3: 40.1 (#147)

BenchmarkGemini 2.5 FlashStep 3
LMArena Coding14241367
SWE-bench Verified (bash only)28.7%—
Aider Polyglot55.1%—
WeirdML41.9%—
ALE-Bench661.88—

Agentic & Tool Use Not comparable

Gemini 2.5 Flash: 30.8 (#74), Step 3: —

BenchmarkGemini 2.5 FlashStep 3
Terminal-Bench17.1%—
Berkeley Function Calling Leaderboard56.2%—
TheAgentCompany41.1%—
BALROG33.5%—
Vending-Bench 2548.84—

Reasoning Step 3 leads

Gemini 2.5 Flash: 18.1 (#286), Step 3: 28.4 (#105)

BenchmarkGemini 2.5 FlashStep 3
Kagi LLM Benchmark56.8%62.3%
LMArena Hard Prompts14221355
ARC-AGI-22.5%—
SimpleBench41.2%—
ARC-AGI-133.3%—
CritPt1.1%—
EnigmaEval2.7%—
DTBench76.5%—
LMCA27.5%—
Epoch Capabilities Index143.03—
ForecastBench60.6—

Math Gemini 2.5 Flash leads

Gemini 2.5 Flash: 39.9 (#98), Step 3: 37.6 (#148)

BenchmarkGemini 2.5 FlashStep 3
LMArena Math14151366
OTIS Mock AIME 2024-202573.1%—
Omni-MATH38.5%—
FrontierMath (Feb 2025 set)4.8%—
FrontierMath Tier 4 (v1)4.2%—

Knowledge Too close to call

Gemini 2.5 Flash: 36.4 (#168), Step 3: 36.8 (#164)

BenchmarkGemini 2.5 FlashStep 3
LMArena Expert14261333
Humanity's Last Exam12.1%—
MMLU-Pro63.9%—
Confabulations16.8%—
Vectara Hallucination Rate7.8%—
GPQA (HELM)39%—

Multimodal Gemini 2.5 Flash leads

Gemini 2.5 Flash: 41.8 (#32), Step 3: 35.5 (#86)

BenchmarkGemini 2.5 FlashStep 3
LMArena Vision12531177
GeoBench76%—
VPCT46.2%—
SpatialViz-Bench36.9%—

Multilingual Gemini 2.5 Flash leads

Gemini 2.5 Flash: 52.3 (#88), Step 3: 46.3 (#159)

BenchmarkGemini 2.5 FlashStep 3
LMArena Non-English14091327
LMArena Chinese14501397
LMArena German14181371
LMArena Korean13851269
LMArena Russian14151331
LMArena Spanish14211371
LMArena French1433—
LMArena Japanese1405—

Instruction Following Gemini 2.5 Flash leads

Gemini 2.5 Flash: 75.7 (#54), Step 3: 70.4 (#164)

BenchmarkGemini 2.5 FlashStep 3
LMArena Instruction Following14051332
IFEval89.8%—

Long Context Gemini 2.5 Flash leads

Gemini 2.5 Flash: 47.5 (#17), Step 3: 40.3 (#157)

BenchmarkGemini 2.5 FlashStep 3
LMArena Longer Query14191326
Fiction.LiveBench77.8%—

Writing & Preference Too close to call

Gemini 2.5 Flash: 53.8 (#157), Step 3: 54.3 (#151)

BenchmarkGemini 2.5 FlashStep 3
LMArena Text14171350
LMArena Creative Writing14001321
LMArena Multi-Turn14081341
Short-Story Creative Writing76.5%—
EQ-Bench Creative Writing1137—
WildBench81.7%—

Frequently asked questions

Is Gemini 2.5 Flash better than Step 3?

Step 3 is the stronger model overall, scoring 40.5 to 39.3 on the Noometry Index.

Is Gemini 2.5 Flash or Step 3 better for coding?

Step 3 scores higher on coding benchmarks: 40.1 versus 35.8 in the Noometry coding category.

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

17 benchmarks have published results for both models. Gemini 2.5 Flash has 54 scored results on Noometry and Step 3 has 17.

Related comparisons

Go deeper