Noometry

Model comparison

Gemini 3.6 Flash vs Step 3

Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 40.5 on the Noometry Index.

Last verified . 16 shared benchmarks.

Gemini 3.6 Flash Google

54.1

Rank #33 Confirmed

Step 3 StepFun

40.5

Rank #149 Confirmed

Summary

  • They share 16 benchmarks with published results for both. Gemini 3.6 Flash scores higher in 9 categories and Step 3 in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Gemini 3.6 Flash leads 67.8 to 36.8.
  • Step 3 has downloadable open weights; the other is API-only.

Side by side

Gemini 3.6 FlashStep 3
ProviderGoogleStepFun
Noometry Index54.140.5
Released2026-07-21—
WeightsProprietaryOpen
Context window1.05M—
Max output66K—
Input $ / M tokens$0.75—
Output $ / M tokens$3.75—
Results tracked4617

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

Category by category

Coding Gemini 3.6 Flash leads

Gemini 3.6 Flash: 50.0 (#48), Step 3: 40.1 (#147)

BenchmarkGemini 3.6 FlashStep 3
LMArena Coding14911367
DeepSWE46.7%—
FrontierCode34.4%—
LMArena WebDev1538—
SciCode52.7%—
WeirdML56.1%—
ALE-Bench715.52—

Agentic & Tool Use Not comparable

Gemini 3.6 Flash: 32.3 (#65), Step 3: —

BenchmarkGemini 3.6 FlashStep 3
APEX-Agents46.9%—
GDP.pdf14%—

Reasoning Gemini 3.6 Flash leads

Gemini 3.6 Flash: 58.8 (#22), Step 3: 28.4 (#105)

BenchmarkGemini 3.6 FlashStep 3
LMArena Hard Prompts14851355
ARC-AGI-260.4%—
Kagi LLM Benchmark—62.3%
NYT Connections (extended)89%—
ARC-AGI-191.2%—
CritPt10.6%—
Chess Puzzles43%—
Mystery Game Puzzles30%—
DTBench95.5%—
LMCA44.9%—
Epoch Capabilities Index154.25—

Math Gemini 3.6 Flash leads

Gemini 3.6 Flash: 57.3 (#40), Step 3: 37.6 (#148)

BenchmarkGemini 3.6 FlashStep 3
LMArena Math15051366
FrontierMath (Tiers 1-3)58.9%—
FrontierMath Tier 422%—
MathArena Final-Answer Competitions70.8%—
OTIS Mock AIME 2024-202594.2%—
ProofBench36%—

Knowledge Gemini 3.6 Flash leads

Gemini 3.6 Flash: 67.8 (#8), Step 3: 36.8 (#164)

BenchmarkGemini 3.6 FlashStep 3
LMArena Expert14881333
GPQA Diamond94.1%—
SimpleQA Verified66.2%—

Multimodal Gemini 3.6 Flash leads

Gemini 3.6 Flash: 38.5 (#64), Step 3: 35.5 (#86)

BenchmarkGemini 3.6 FlashStep 3
LMArena Vision12981177
Blueprint-Bench 231.2%—
Furniture Assembly23.3%—
LMArena Document1456—

Multilingual Gemini 3.6 Flash leads

Gemini 3.6 Flash: 56.5 (#19), Step 3: 46.3 (#159)

BenchmarkGemini 3.6 FlashStep 3
LMArena Non-English14691327
LMArena Chinese15311397
LMArena German14781371
LMArena Korean14311269
LMArena Russian14871331
LMArena Spanish14751371
LMArena French1504—
LMArena Japanese1476—

Instruction Following Gemini 3.6 Flash leads

Gemini 3.6 Flash: 77.0 (#33), Step 3: 70.4 (#164)

BenchmarkGemini 3.6 FlashStep 3
LMArena Instruction Following14661332

Long Context Gemini 3.6 Flash leads

Gemini 3.6 Flash: 45.1 (#50), Step 3: 40.3 (#157)

BenchmarkGemini 3.6 FlashStep 3
LMArena Longer Query14741326

Writing & Preference Gemini 3.6 Flash leads

Gemini 3.6 Flash: 68.2 (#27), Step 3: 54.3 (#151)

BenchmarkGemini 3.6 FlashStep 3
LMArena Text14791350
LMArena Creative Writing14651321
LMArena Multi-Turn14811341
EQ-Bench Creative Writing1604—

Frequently asked questions

Is Gemini 3.6 Flash better than Step 3?

Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 40.5 on the Noometry Index.

Is Gemini 3.6 Flash or Step 3 better for coding?

Gemini 3.6 Flash scores higher on coding benchmarks: 50.0 versus 40.1 in the Noometry coding category.

How many benchmarks do Gemini 3.6 Flash and Step 3 share?

16 benchmarks have published results for both models. Gemini 3.6 Flash has 46 scored results on Noometry and Step 3 has 17.

Related comparisons

Go deeper