Noometry

Model comparison

Gemini 3.1 Pro Preview vs Step 3.5 Flash

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 42.3 on the Noometry Index. Step 3.5 Flash costs 30× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.

Last verified . 19 shared benchmarks.

Gemini 3.1 Pro Preview Google

56.7

Rank #23 Confirmed

Step 3.5 Flash StepFun

42.3

Rank #116 Confirmed

Summary

  • They share 19 benchmarks with published results for both. Gemini 3.1 Pro Preview scores higher in 8 categories and Step 3.5 Flash in 0 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Gemini 3.1 Pro Preview leads 71.7 to 22.2.
  • The biggest single-benchmark swing is NYT Connections (extended): 97.4% for Gemini 3.1 Pro Preview and 28.4% for Step 3.5 Flash.
  • Step 3.5 Flash is cheaper at $0.10 / $0.30 per million input/output tokens, against $2 / $12 for Gemini 3.1 Pro Preview.
  • Gemini 3.1 Pro Preview accepts more context: 1.05M tokens versus 256K.
  • Step 3.5 Flash has downloadable open weights; the other is API-only.

Side by side

Gemini 3.1 Pro PreviewStep 3.5 Flash
ProviderGoogleStepFun
Noometry Index56.742.3
Released2026-02-192026-01-29
WeightsProprietaryOpen
Context window1.05M256K
Max output66K256K
Input $ / M tokens$2$0.10
Output $ / M tokens$12$0.30
Results tracked7119

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

Category by category

Coding Too close to call

Gemini 3.1 Pro Preview: 42.5 (#99), Step 3.5 Flash: 42.4 (#105)

BenchmarkGemini 3.1 Pro PreviewStep 3.5 Flash
LMArena Coding14841436
SWE-bench Verified75.6%—
DeepSWE11.7%—
LMArena WebDev1447—
SciCode58.9%—
GSO22.6%—
WeirdML72.1%—
MirrorCode8.9%—
ALE-Bench1,161—
AlgoTune2.02—

Agentic & Tool Use Not comparable

Gemini 3.1 Pro Preview: 37.7 (#34), Step 3.5 Flash: —

BenchmarkGemini 3.1 Pro PreviewStep 3.5 Flash
Terminal-Bench80.2%—
APEX-Agents35.3%—
τ²-bench Banking26%—
DeepResearch Bench47.8%—
PostTrainBench22%—
BALROG57%—
ExploitBench26.1%—
GBAEval0.8%—
GDP.pdf17%—
LMArena Search1211—
METR Time Horizons77%—
Vending-Bench 23,774—

Reasoning Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 71.7 (#12), Step 3.5 Flash: 22.2 (#202)

BenchmarkGemini 3.1 Pro PreviewStep 3.5 Flash
NYT Connections (extended)97.4%28.4%
LMArena Hard Prompts14851411
ARC-AGI-277.1%—
SimpleBench79.6%—
ARC-AGI-198%—
CritPt17.7%—
Chess Puzzles55%—
EnigmaEval36.8%—
Thematic Generalization79.4%—
EBR-Bench14.3%—
Mystery Game Puzzles34%—
DTBench97.1%—
LMCA53.8%—
Epoch Capabilities Index154.77—
ForecastBench59—

Math Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 62.1 (#34), Step 3.5 Flash: 42.6 (#84)

BenchmarkGemini 3.1 Pro PreviewStep 3.5 Flash
MathArena Final-Answer Competitions86.5%66.8%
LMArena Math14851408
FrontierMath (Tiers 1-3)59.6%—
FrontierMath Tier 426.8%—
OTIS Mock AIME 2024-202595.6%—
ProofBench26%—
FrontierMath (Feb 2025 set)36.9%—
FrontierMath Tier 4 (v1)16.7%—

Knowledge Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 71.8 (#3), Step 3.5 Flash: 39.6 (#132)

BenchmarkGemini 3.1 Pro PreviewStep 3.5 Flash
LMArena Expert14851421
GPQA Diamond94.4%—
Humanity's Last Exam46.4%—
SimpleQA Verified73.5%—
Vectara Hallucination Rate10.4%—

Multimodal Not comparable

Gemini 3.1 Pro Preview: 37.9 (#69), Step 3.5 Flash: —

BenchmarkGemini 3.1 Pro PreviewStep 3.5 Flash
LMArena Vision1296—
Blueprint-Bench 226.5%—
Furniture Assembly26.7%—
LMArena Document1444—

Multilingual Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 57.0 (#12), Step 3.5 Flash: 50.5 (#119)

BenchmarkGemini 3.1 Pro PreviewStep 3.5 Flash
LMArena Non-English14771385
LMArena Chinese15291447
LMArena French14871421
LMArena German14911405
LMArena Japanese14931354
LMArena Korean14551352
LMArena Russian14981385
LMArena Spanish14791419

Instruction Following Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 77.0 (#32), Step 3.5 Flash: 73.1 (#124)

BenchmarkGemini 3.1 Pro PreviewStep 3.5 Flash
LMArena Instruction Following14661385

Long Context Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 47.4 (#18), Step 3.5 Flash: 42.8 (#117)

BenchmarkGemini 3.1 Pro PreviewStep 3.5 Flash
LMArena Longer Query14831402
CL-bench20.8%—
CL-bench Life16.9%—

Writing & Preference Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 66.1 (#37), Step 3.5 Flash: 58.8 (#113)

BenchmarkGemini 3.1 Pro PreviewStep 3.5 Flash
LMArena Text14811403
LMArena Creative Writing14821357
LMArena Multi-Turn14881405
EQ-Bench Creative Writing1491—
EQ-Bench 41142—

Frequently asked questions

Is Gemini 3.1 Pro Preview better than Step 3.5 Flash?

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 42.3 on the Noometry Index. Step 3.5 Flash costs 30× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.

Which is cheaper, Gemini 3.1 Pro Preview or Step 3.5 Flash?

Step 3.5 Flash is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Gemini 3.1 Pro Preview lists at $2 and $12.

Is Gemini 3.1 Pro Preview or Step 3.5 Flash better for coding?

They score almost the same on coding (42.5 vs 42.4); test both on your own repository before choosing.

Which has the bigger context window?

Gemini 3.1 Pro Preview does, with 1.05M tokens against 256K.

How many benchmarks do Gemini 3.1 Pro Preview and Step 3.5 Flash share?

19 benchmarks have published results for both models. Gemini 3.1 Pro Preview has 71 scored results on Noometry and Step 3.5 Flash has 19.

Related comparisons

Go deeper