Noometry

Model comparison

Gemini 3.1 Pro Preview vs Gemini 3.6 Flash

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 54.1 on the Noometry Index. Gemini 3.6 Flash costs 3.0× 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 . 45 shared benchmarks.

Gemini 3.1 Pro Preview Google

56.7

Rank #23 Confirmed

Gemini 3.6 Flash Google

54.1

Rank #33 Confirmed

Summary

  • They share 45 benchmarks with published results for both. Gemini 3.1 Pro Preview scores higher in 7 categories and Gemini 3.6 Flash in 3 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Gemini 3.1 Pro Preview leads 71.7 to 58.8.
  • The biggest single-benchmark swing is DeepSWE: 11.7% for Gemini 3.1 Pro Preview and 46.7% for Gemini 3.6 Flash.
  • Gemini 3.6 Flash is cheaper at $0.75 / $3.75 per million input/output tokens, against $2 / $12 for Gemini 3.1 Pro Preview.

Side by side

Gemini 3.1 Pro PreviewGemini 3.6 Flash
ProviderGoogleGoogle
Noometry Index56.754.1
Released2026-02-192026-07-21
WeightsProprietaryProprietary
Context window1.05M1.05M
Max output66K66K
Input $ / M tokens$2$0.75
Output $ / M tokens$12$3.75
Results tracked7146

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

Category by category

Coding Gemini 3.6 Flash leads

Gemini 3.1 Pro Preview: 42.5 (#99), Gemini 3.6 Flash: 50.0 (#48)

BenchmarkGemini 3.1 Pro PreviewGemini 3.6 Flash
DeepSWE11.7%46.7%
LMArena WebDev14471538
SciCode58.9%52.7%
WeirdML72.1%56.1%
LMArena Coding14841491
ALE-Bench1,161715.52
SWE-bench Verified75.6%—
FrontierCode—34.4%
GSO22.6%—
MirrorCode8.9%—
AlgoTune2.02—

Agentic & Tool Use Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 37.7 (#34), Gemini 3.6 Flash: 32.3 (#65)

BenchmarkGemini 3.1 Pro PreviewGemini 3.6 Flash
APEX-Agents35.3%46.9%
GDP.pdf17%14%
Terminal-Bench80.2%—
τ²-bench Banking26%—
DeepResearch Bench47.8%—
PostTrainBench22%—
BALROG57%—
ExploitBench26.1%—
GBAEval0.8%—
LMArena Search1211—
METR Time Horizons77%—
Vending-Bench 23,774—

Reasoning Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 71.7 (#12), Gemini 3.6 Flash: 58.8 (#22)

BenchmarkGemini 3.1 Pro PreviewGemini 3.6 Flash
ARC-AGI-277.1%60.4%
NYT Connections (extended)97.4%89%
ARC-AGI-198%91.2%
CritPt17.7%10.6%
Chess Puzzles55%43%
LMArena Hard Prompts14851485
Mystery Game Puzzles34%30%
DTBench97.1%95.5%
LMCA53.8%44.9%
Epoch Capabilities Index154.77154.25
SimpleBench79.6%—
EnigmaEval36.8%—
Thematic Generalization79.4%—
EBR-Bench14.3%—
ForecastBench59—

Math Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 62.1 (#34), Gemini 3.6 Flash: 57.3 (#40)

BenchmarkGemini 3.1 Pro PreviewGemini 3.6 Flash
FrontierMath (Tiers 1-3)59.6%58.9%
FrontierMath Tier 426.8%22%
MathArena Final-Answer Competitions86.5%70.8%
OTIS Mock AIME 2024-202595.6%94.2%
ProofBench26%36%
LMArena Math14851505
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), Gemini 3.6 Flash: 67.8 (#8)

BenchmarkGemini 3.1 Pro PreviewGemini 3.6 Flash
GPQA Diamond94.4%94.1%
SimpleQA Verified73.5%66.2%
LMArena Expert14851488
Humanity's Last Exam46.4%—
Vectara Hallucination Rate10.4%—

Multimodal Too close to call

Gemini 3.1 Pro Preview: 37.9 (#69), Gemini 3.6 Flash: 38.5 (#64)

BenchmarkGemini 3.1 Pro PreviewGemini 3.6 Flash
LMArena Vision12961298
Blueprint-Bench 226.5%31.2%
Furniture Assembly26.7%23.3%
LMArena Document14441456

Multilingual Too close to call

Gemini 3.1 Pro Preview: 57.0 (#12), Gemini 3.6 Flash: 56.5 (#19)

BenchmarkGemini 3.1 Pro PreviewGemini 3.6 Flash
LMArena Non-English14771469
LMArena Chinese15291531
LMArena French14871504
LMArena German14911478
LMArena Japanese14931476
LMArena Korean14551431
LMArena Russian14981487
LMArena Spanish14791475

Instruction Following Too close to call

Gemini 3.1 Pro Preview: 77.0 (#32), Gemini 3.6 Flash: 77.0 (#33)

BenchmarkGemini 3.1 Pro PreviewGemini 3.6 Flash
LMArena Instruction Following14661466

Long Context Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 47.4 (#18), Gemini 3.6 Flash: 45.1 (#50)

BenchmarkGemini 3.1 Pro PreviewGemini 3.6 Flash
LMArena Longer Query14831474
CL-bench20.8%—
CL-bench Life16.9%—

Writing & Preference Gemini 3.6 Flash leads

Gemini 3.1 Pro Preview: 66.1 (#37), Gemini 3.6 Flash: 68.2 (#27)

BenchmarkGemini 3.1 Pro PreviewGemini 3.6 Flash
LMArena Text14811479
LMArena Creative Writing14821465
EQ-Bench Creative Writing14911604
LMArena Multi-Turn14881481
EQ-Bench 41142—

Frequently asked questions

Is Gemini 3.1 Pro Preview better than Gemini 3.6 Flash?

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 54.1 on the Noometry Index. Gemini 3.6 Flash costs 3.0× 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 Gemini 3.6 Flash?

Gemini 3.6 Flash is cheaper. It lists at $0.75 per million input tokens and $3.75 per million output tokens; Gemini 3.1 Pro Preview lists at $2 and $12.

Is Gemini 3.1 Pro Preview or Gemini 3.6 Flash better for coding?

Gemini 3.6 Flash scores higher on coding benchmarks: 50.0 versus 42.5 in the Noometry coding category.

Which has the bigger context window?

Both accept 1.05M tokens.

How many benchmarks do Gemini 3.1 Pro Preview and Gemini 3.6 Flash share?

45 benchmarks have published results for both models. Gemini 3.1 Pro Preview has 71 scored results on Noometry and Gemini 3.6 Flash has 46.

Related comparisons

Go deeper