Noometry

Model comparison

Gemini 3.5 Flash vs Step 3

Gemini 3.5 Flash is the stronger model overall, scoring 54.2 to 40.5 on the Noometry Index.

Last verified . 16 shared benchmarks.

Gemini 3.5 Flash Google

54.2

Rank #32 Confirmed

Step 3 StepFun

40.5

Rank #149 Confirmed

Summary

  • They share 16 benchmarks with published results for both. Gemini 3.5 Flash scores higher in 9 categories and Step 3 in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Gemini 3.5 Flash leads 62.8 to 28.4.
  • Step 3 has downloadable open weights; the other is API-only.

Side by side

Gemini 3.5 FlashStep 3
ProviderGoogleStepFun
Noometry Index54.240.5
Released2026-05-19—
WeightsProprietaryOpen
Context window1.05M—
Max output66K—
Input $ / M tokens$1.50—
Output $ / M tokens$9—
Results tracked5417

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

Category by category

Coding Gemini 3.5 Flash leads

Gemini 3.5 Flash: 49.4 (#49), Step 3: 40.1 (#147)

BenchmarkGemini 3.5 FlashStep 3
LMArena Coding14921367
SWE-bench Verified79.3%—
DeepSWE37.4%—
LMArena WebDev1499—
SciCode53.1%—
WeirdML62.6%—
ALE-Bench911.02—

Agentic & Tool Use Not comparable

Gemini 3.5 Flash: 24.7 (#114), Step 3: —

BenchmarkGemini 3.5 FlashStep 3
APEX-Agents27.5%—
GBAEval6.7%—
GDP.pdf14%—
Vending-Bench 25,396—

Reasoning Gemini 3.5 Flash leads

Gemini 3.5 Flash: 62.8 (#18), Step 3: 28.4 (#105)

BenchmarkGemini 3.5 FlashStep 3
LMArena Hard Prompts14881355
ARC-AGI-272.1%—
SimpleBench76.7%—
Kagi LLM Benchmark—62.3%
NYT Connections (extended)92.6%—
ARC-AGI-192.5%—
CritPt13.1%—
Chess Puzzles50%—
EnigmaEval25.4%—
EBR-Bench4.8%—
Mystery Game Puzzles32%—
DTBench94.7%—
LMCA47.1%—
Surface Evolver Bench58.1%—
Epoch Capabilities Index154.46—
ForecastBench59—

Math Gemini 3.5 Flash leads

Gemini 3.5 Flash: 60.7 (#36), Step 3: 37.6 (#148)

BenchmarkGemini 3.5 FlashStep 3
LMArena Math15041366
FrontierMath (Tiers 1-3)62.8%—
FrontierMath Tier 426.8%—
MathArena Final-Answer Competitions76.3%—
OTIS Mock AIME 2024-202595.6%—
ProofBench31%—
FrontierMath (Feb 2025 set)39%—
FrontierMath Tier 4 (v1)14.6%—

Knowledge Gemini 3.5 Flash leads

Gemini 3.5 Flash: 66.3 (#11), Step 3: 36.8 (#164)

BenchmarkGemini 3.5 FlashStep 3
LMArena Expert14951333
GPQA Diamond92.8%—
SimpleQA Verified66.2%—

Multimodal Gemini 3.5 Flash leads

Gemini 3.5 Flash: 45.7 (#15), Step 3: 35.5 (#86)

BenchmarkGemini 3.5 FlashStep 3
LMArena Vision13101177
Blueprint-Bench 233.6%—
LMArena Document1463—

Multilingual Gemini 3.5 Flash leads

Gemini 3.5 Flash: 57.0 (#13), Step 3: 46.3 (#159)

BenchmarkGemini 3.5 FlashStep 3
LMArena Non-English14761327
LMArena Chinese15261397
LMArena German14921371
LMArena Korean14511269
LMArena Russian14931331
LMArena Spanish14801371
LMArena French1490—
LMArena Japanese1486—

Instruction Following Gemini 3.5 Flash leads

Gemini 3.5 Flash: 77.0 (#30), Step 3: 70.4 (#164)

BenchmarkGemini 3.5 FlashStep 3
LMArena Instruction Following14671332

Long Context Gemini 3.5 Flash leads

Gemini 3.5 Flash: 45.4 (#38), Step 3: 40.3 (#157)

BenchmarkGemini 3.5 FlashStep 3
LMArena Longer Query14821326

Writing & Preference Gemini 3.5 Flash leads

Gemini 3.5 Flash: 65.5 (#47), Step 3: 54.3 (#151)

BenchmarkGemini 3.5 FlashStep 3
LMArena Text14821350
LMArena Creative Writing14701321
LMArena Multi-Turn14811341
EQ-Bench 41087—

Frequently asked questions

Is Gemini 3.5 Flash better than Step 3?

Gemini 3.5 Flash is the stronger model overall, scoring 54.2 to 40.5 on the Noometry Index.

Is Gemini 3.5 Flash or Step 3 better for coding?

Gemini 3.5 Flash scores higher on coding benchmarks: 49.4 versus 40.1 in the Noometry coding category.

How many benchmarks do Gemini 3.5 Flash and Step 3 share?

16 benchmarks have published results for both models. Gemini 3.5 Flash has 54 scored results on Noometry and Step 3 has 17.

Related comparisons

Go deeper