Noometry

Model comparison

Gemini 3.7 Flash vs Step 3

Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 40.5 on the Noometry Index.

Last verified . 16 shared benchmarks.

Gemini 3.7 Flash Google

59.8

Rank #14 Confirmed

Step 3 StepFun

40.5

Rank #149 Confirmed

Summary

  • They share 16 benchmarks with published results for both. Gemini 3.7 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 3.7 Flash leads 70.0 to 28.4.
  • Step 3 has downloadable open weights; the other is API-only.

Side by side

Gemini 3.7 FlashStep 3
ProviderGoogleStepFun
Noometry Index59.840.5
Released2026-08-13—
WeightsProprietaryOpen
Context window1.05M—
Max output66K—
Input $ / M tokens$0.75—
Output $ / M tokens$3.75—
Results tracked4417

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

Category by category

Coding Gemini 3.7 Flash leads

Gemini 3.7 Flash: 56.2 (#22), Step 3: 40.1 (#147)

BenchmarkGemini 3.7 FlashStep 3
LMArena Coding14971367
DeepSWE65.5%—
FrontierCode43.6%—
LMArena WebDev1592—
FrontierSWE20.3%—
SciCode59.8%—
ALE-Bench904.3—

Agentic & Tool Use Not comparable

Gemini 3.7 Flash: 42.1 (#19), Step 3: —

BenchmarkGemini 3.7 FlashStep 3
APEX-Agents67.8%—
Remote Labor Index5%—
GDP.pdf23.8%—

Reasoning Gemini 3.7 Flash leads

Gemini 3.7 Flash: 70.0 (#15), Step 3: 28.4 (#105)

BenchmarkGemini 3.7 FlashStep 3
LMArena Hard Prompts14941355
ARC-AGI-284.6%—
Kagi LLM Benchmark—62.3%
NYT Connections (extended)94%—
ARC-AGI-195.5%—
CritPt14.3%—
Chess Puzzles47%—
Mystery Game Puzzles37%—
DTBench96.8%—
LMCA50.4%—
Epoch Capabilities Index157.27—

Math Gemini 3.7 Flash leads

Gemini 3.7 Flash: 69.6 (#23), Step 3: 37.6 (#148)

BenchmarkGemini 3.7 FlashStep 3
LMArena Math15071366
FrontierMath (Tiers 1-3)71.6%—
FrontierMath Tier 436.6%—
OTIS Mock AIME 2024-202597.2%—
ProofBench58%—

Knowledge Gemini 3.7 Flash leads

Gemini 3.7 Flash: 69.7 (#5), Step 3: 36.8 (#164)

BenchmarkGemini 3.7 FlashStep 3
LMArena Expert15081333
GPQA Diamond94.8%—
SimpleQA Verified69.2%—

Multimodal Gemini 3.7 Flash leads

Gemini 3.7 Flash: 37.3 (#73), Step 3: 35.5 (#86)

BenchmarkGemini 3.7 FlashStep 3
LMArena Vision13161177
Furniture Assembly26.7%—

Multilingual Gemini 3.7 Flash leads

Gemini 3.7 Flash: 57.6 (#7), Step 3: 46.3 (#159)

BenchmarkGemini 3.7 FlashStep 3
LMArena Non-English14841327
LMArena Chinese15481397
LMArena German14981371
LMArena Korean14831269
LMArena Russian15161331
LMArena Spanish15031371
LMArena French1505—
LMArena Japanese1512—

Instruction Following Gemini 3.7 Flash leads

Gemini 3.7 Flash: 77.7 (#15), Step 3: 70.4 (#164)

BenchmarkGemini 3.7 FlashStep 3
LMArena Instruction Following14831332

Long Context Gemini 3.7 Flash leads

Gemini 3.7 Flash: 45.7 (#30), Step 3: 40.3 (#157)

BenchmarkGemini 3.7 FlashStep 3
LMArena Longer Query14921326

Writing & Preference Gemini 3.7 Flash leads

Gemini 3.7 Flash: 71.2 (#20), Step 3: 54.3 (#151)

BenchmarkGemini 3.7 FlashStep 3
LMArena Text14861350
LMArena Creative Writing14901321
LMArena Multi-Turn14891341
EQ-Bench Creative Writing1723—

Frequently asked questions

Is Gemini 3.7 Flash better than Step 3?

Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 40.5 on the Noometry Index.

Is Gemini 3.7 Flash or Step 3 better for coding?

Gemini 3.7 Flash scores higher on coding benchmarks: 56.2 versus 40.1 in the Noometry coding category.

How many benchmarks do Gemini 3.7 Flash and Step 3 share?

16 benchmarks have published results for both models. Gemini 3.7 Flash has 44 scored results on Noometry and Step 3 has 17.

Related comparisons

Go deeper