Noometry

Model comparison

Gemini 3.1 Pro Preview vs Gemini 3 Flash Preview

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 52.3 on the Noometry Index. Gemini 3 Flash Preview costs 4.0× 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 . 52 shared benchmarks.

Gemini 3.1 Pro Preview Google

56.7

Rank #23 Confirmed

Gemini 3 Flash Preview Google

52.3

Rank #40 Confirmed

Summary

  • They share 52 benchmarks with published results for both. Gemini 3.1 Pro Preview scores higher in 7 categories and Gemini 3 Flash Preview in 3 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Gemini 3.1 Pro Preview leads 71.7 to 49.2.
  • The biggest single-benchmark swing is ARC-AGI-2: 77.1% for Gemini 3.1 Pro Preview and 33.6% for Gemini 3 Flash Preview.
  • Gemini 3 Flash Preview is cheaper at $0.50 / $3 per million input/output tokens, against $2 / $12 for Gemini 3.1 Pro Preview.

Side by side

Gemini 3.1 Pro PreviewGemini 3 Flash Preview
ProviderGoogleGoogle
Noometry Index56.752.3
Released2026-02-192025-12-17
WeightsProprietaryProprietary
Context window1.05M1.05M
Max output66K66K
Input $ / M tokens$2$0.50
Output $ / M tokens$12$3
Results tracked7159

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

Category by category

Coding Gemini 3 Flash Preview leads

Gemini 3.1 Pro Preview: 42.5 (#99), Gemini 3 Flash Preview: 50.9 (#42)

BenchmarkGemini 3.1 Pro PreviewGemini 3 Flash Preview
SWE-bench Verified75.6%75.4%
LMArena WebDev14471439
GSO22.6%9.8%
WeirdML72.1%61.6%
LMArena Coding14841460
ALE-Bench1,1611,367
DeepSWE11.7%—
SWE-bench Verified (bash only)—75.8%
SWE-bench Multilingual—72.7%
SciCode58.9%—
MirrorCode8.9%—
AlgoTune2.02—

Agentic & Tool Use Gemini 3 Flash Preview leads

Gemini 3.1 Pro Preview: 37.7 (#34), Gemini 3 Flash Preview: 38.7 (#29)

BenchmarkGemini 3.1 Pro PreviewGemini 3 Flash Preview
Terminal-Bench80.2%64.3%
τ²-bench Banking26%27.3%
DeepResearch Bench47.8%49.8%
BALROG57%48.1%
GDP.pdf17%10%
LMArena Search12111198
Vending-Bench 23,7743,635
APEX-Agents35.3%—
τ²-bench Airline—82.5%
τ²-bench Retail—76.8%
τ²-bench Telecom—91.2%
PostTrainBench22%—
ExploitBench26.1%—
GBAEval0.8%—
METR Time Horizons77%—

Reasoning Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 71.7 (#12), Gemini 3 Flash Preview: 49.2 (#37)

BenchmarkGemini 3.1 Pro PreviewGemini 3 Flash Preview
ARC-AGI-277.1%33.6%
SimpleBench79.6%61.1%
NYT Connections (extended)97.4%83.1%
ARC-AGI-198%84.7%
Chess Puzzles55%40%
LMArena Hard Prompts14851465
Mystery Game Puzzles34%26%
DTBench97.1%89.1%
LMCA53.8%43.1%
Epoch Capabilities Index154.77151.8
ForecastBench5958.5
CritPt17.7%—
EnigmaEval36.8%—
Thematic Generalization79.4%—
EBR-Bench14.3%—

Math Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 62.1 (#34), Gemini 3 Flash Preview: 51.7 (#55)

BenchmarkGemini 3.1 Pro PreviewGemini 3 Flash Preview
FrontierMath (Tiers 1-3)59.6%51.2%
FrontierMath Tier 426.8%17.1%
MathArena Final-Answer Competitions86.5%67.6%
OTIS Mock AIME 2024-202595.6%95.6%
ProofBench26%15%
LMArena Math14851473
FrontierMath (Feb 2025 set)36.9%35.6%
FrontierMath Tier 4 (v1)16.7%4.2%

Knowledge Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 71.8 (#3), Gemini 3 Flash Preview: 58.8 (#33)

BenchmarkGemini 3.1 Pro PreviewGemini 3 Flash Preview
GPQA Diamond94.4%89.4%
SimpleQA Verified73.5%66.8%
Vectara Hallucination Rate10.4%13.5%
LMArena Expert14851462
Humanity's Last Exam46.4%—

Multimodal Gemini 3 Flash Preview leads

Gemini 3.1 Pro Preview: 37.9 (#69), Gemini 3 Flash Preview: 45.5 (#16)

BenchmarkGemini 3.1 Pro PreviewGemini 3 Flash Preview
LMArena Vision12961285
Blueprint-Bench 226.5%0%
LMArena Document14441413
GeoBench—88%
VPCT—72.6%
Furniture Assembly26.7%—

Multilingual Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 57.0 (#12), Gemini 3 Flash Preview: 55.7 (#27)

BenchmarkGemini 3.1 Pro PreviewGemini 3 Flash Preview
LMArena Non-English14771458
LMArena Chinese15291511
LMArena French14871477
LMArena German14911497
LMArena Japanese14931489
LMArena Korean14551443
LMArena Russian14981480
LMArena Spanish14791469

Instruction Following Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 77.0 (#32), Gemini 3 Flash Preview: 75.7 (#56)

BenchmarkGemini 3.1 Pro PreviewGemini 3 Flash Preview
LMArena Instruction Following14661437

Long Context Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 47.4 (#18), Gemini 3 Flash Preview: 44.4 (#67)

BenchmarkGemini 3.1 Pro PreviewGemini 3 Flash Preview
LMArena Longer Query14831452
CL-bench20.8%—
CL-bench Life16.9%—

Writing & Preference Too close to call

Gemini 3.1 Pro Preview: 66.1 (#37), Gemini 3 Flash Preview: 65.5 (#45)

BenchmarkGemini 3.1 Pro PreviewGemini 3 Flash Preview
LMArena Text14811466
LMArena Creative Writing14821457
LMArena Multi-Turn14881471
EQ-Bench Creative Writing1491—
EQ-Bench 41142—

Frequently asked questions

Is Gemini 3.1 Pro Preview better than Gemini 3 Flash Preview?

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 52.3 on the Noometry Index. Gemini 3 Flash Preview costs 4.0× 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 Flash Preview?

Gemini 3 Flash Preview is cheaper. It lists at $0.50 per million input tokens and $3 per million output tokens; Gemini 3.1 Pro Preview lists at $2 and $12.

Is Gemini 3.1 Pro Preview or Gemini 3 Flash Preview better for coding?

Gemini 3 Flash Preview scores higher on coding benchmarks: 50.9 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 Flash Preview share?

52 benchmarks have published results for both models. Gemini 3.1 Pro Preview has 71 scored results on Noometry and Gemini 3 Flash Preview has 59.

Related comparisons

Go deeper