Noometry

Model comparison

Gemini 2.5 Flash vs Gemini 3.1 Pro Preview

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 39.3 on the Noometry Index. Gemini 2.5 Flash costs 5.3× 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 . 38 shared benchmarks.

Gemini 2.5 Flash Google

39.3

Rank #170 Confirmed

Gemini 3.1 Pro Preview Google

56.7

Rank #23 Confirmed

Summary

  • They share 38 benchmarks with published results for both. Gemini 2.5 Flash scores higher in 2 categories and Gemini 3.1 Pro Preview in 8 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Gemini 3.1 Pro Preview leads 71.7 to 18.1.
  • The biggest single-benchmark swing is ARC-AGI-2: 2.5% for Gemini 2.5 Flash and 77.1% for Gemini 3.1 Pro Preview.
  • Gemini 2.5 Flash is cheaper at $0.30 / $2.50 per million input/output tokens, against $2 / $12 for Gemini 3.1 Pro Preview.

Side by side

Gemini 2.5 FlashGemini 3.1 Pro Preview
ProviderGoogleGoogle
Noometry Index39.356.7
Released2025-04-172026-02-19
WeightsProprietaryProprietary
Context window1.05M1.05M
Max output66K66K
Input $ / M tokens$0.30$2
Output $ / M tokens$2.50$12
Results tracked5471

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

Category by category

Coding Gemini 3.1 Pro Preview leads

Gemini 2.5 Flash: 35.8 (#220), Gemini 3.1 Pro Preview: 42.5 (#99)

BenchmarkGemini 2.5 FlashGemini 3.1 Pro Preview
WeirdML41.9%72.1%
LMArena Coding14241484
ALE-Bench661.881,161
SWE-bench Verified—75.6%
DeepSWE—11.7%
SWE-bench Verified (bash only)28.7%—
Aider Polyglot55.1%—
LMArena WebDev—1447
SciCode—58.9%
GSO—22.6%
MirrorCode—8.9%
AlgoTune—2.02

Agentic & Tool Use Gemini 3.1 Pro Preview leads

Gemini 2.5 Flash: 30.8 (#74), Gemini 3.1 Pro Preview: 37.7 (#34)

BenchmarkGemini 2.5 FlashGemini 3.1 Pro Preview
Terminal-Bench17.1%80.2%
BALROG33.5%57%
Vending-Bench 2548.843,774
APEX-Agents—35.3%
Berkeley Function Calling Leaderboard56.2%—
TheAgentCompany41.1%—
τ²-bench Banking—26%
DeepResearch Bench—47.8%
PostTrainBench—22%
ExploitBench—26.1%
GBAEval—0.8%
GDP.pdf—17%
LMArena Search—1211
METR Time Horizons—77%

Reasoning Gemini 3.1 Pro Preview leads

Gemini 2.5 Flash: 18.1 (#286), Gemini 3.1 Pro Preview: 71.7 (#12)

BenchmarkGemini 2.5 FlashGemini 3.1 Pro Preview
ARC-AGI-22.5%77.1%
SimpleBench41.2%79.6%
ARC-AGI-133.3%98%
CritPt1.1%17.7%
EnigmaEval2.7%36.8%
LMArena Hard Prompts14221485
DTBench76.5%97.1%
LMCA27.5%53.8%
Epoch Capabilities Index143.03154.77
ForecastBench60.659
Kagi LLM Benchmark56.8%—
NYT Connections (extended)—97.4%
Chess Puzzles—55%
Thematic Generalization—79.4%
EBR-Bench—14.3%
Mystery Game Puzzles—34%

Math Gemini 3.1 Pro Preview leads

Gemini 2.5 Flash: 39.9 (#98), Gemini 3.1 Pro Preview: 62.1 (#34)

BenchmarkGemini 2.5 FlashGemini 3.1 Pro Preview
OTIS Mock AIME 2024-202573.1%95.6%
LMArena Math14151485
FrontierMath (Feb 2025 set)4.8%36.9%
FrontierMath Tier 4 (v1)4.2%16.7%
FrontierMath (Tiers 1-3)—59.6%
FrontierMath Tier 4—26.8%
MathArena Final-Answer Competitions—86.5%
ProofBench—26%
Omni-MATH38.5%—

Knowledge Gemini 3.1 Pro Preview leads

Gemini 2.5 Flash: 36.4 (#168), Gemini 3.1 Pro Preview: 71.8 (#3)

BenchmarkGemini 2.5 FlashGemini 3.1 Pro Preview
Humanity's Last Exam12.1%46.4%
Vectara Hallucination Rate7.8%10.4%
LMArena Expert14261485
GPQA Diamond—94.4%
SimpleQA Verified—73.5%
MMLU-Pro63.9%—
Confabulations16.8%—
GPQA (HELM)39%—

Multimodal Gemini 2.5 Flash leads

Gemini 2.5 Flash: 41.8 (#32), Gemini 3.1 Pro Preview: 37.9 (#69)

BenchmarkGemini 2.5 FlashGemini 3.1 Pro Preview
LMArena Vision12531296
GeoBench76%—
VPCT46.2%—
Blueprint-Bench 2—26.5%
Furniture Assembly—26.7%
LMArena Document—1444
SpatialViz-Bench36.9%—

Multilingual Gemini 3.1 Pro Preview leads

Gemini 2.5 Flash: 52.3 (#88), Gemini 3.1 Pro Preview: 57.0 (#12)

BenchmarkGemini 2.5 FlashGemini 3.1 Pro Preview
LMArena Non-English14091477
LMArena Chinese14501529
LMArena French14331487
LMArena German14181491
LMArena Japanese14051493
LMArena Korean13851455
LMArena Russian14151498
LMArena Spanish14211479

Instruction Following Gemini 3.1 Pro Preview leads

Gemini 2.5 Flash: 75.7 (#54), Gemini 3.1 Pro Preview: 77.0 (#32)

BenchmarkGemini 2.5 FlashGemini 3.1 Pro Preview
LMArena Instruction Following14051466
IFEval89.8%—

Long Context Too close to call

Gemini 2.5 Flash: 47.5 (#17), Gemini 3.1 Pro Preview: 47.4 (#18)

BenchmarkGemini 2.5 FlashGemini 3.1 Pro Preview
LMArena Longer Query14191483
Fiction.LiveBench77.8%—
CL-bench—20.8%
CL-bench Life—16.9%

Writing & Preference Gemini 3.1 Pro Preview leads

Gemini 2.5 Flash: 53.8 (#157), Gemini 3.1 Pro Preview: 66.1 (#37)

BenchmarkGemini 2.5 FlashGemini 3.1 Pro Preview
LMArena Text14171481
LMArena Creative Writing14001482
EQ-Bench Creative Writing11371491
LMArena Multi-Turn14081488
Short-Story Creative Writing76.5%—
WildBench81.7%—
EQ-Bench 4—1142

Frequently asked questions

Is Gemini 2.5 Flash better than Gemini 3.1 Pro Preview?

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 39.3 on the Noometry Index. Gemini 2.5 Flash costs 5.3× 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 2.5 Flash or Gemini 3.1 Pro Preview?

Gemini 2.5 Flash is cheaper. It lists at $0.30 per million input tokens and $2.50 per million output tokens; Gemini 3.1 Pro Preview lists at $2 and $12.

Is Gemini 2.5 Flash or Gemini 3.1 Pro Preview better for coding?

Gemini 3.1 Pro Preview scores higher on coding benchmarks: 42.5 versus 35.8 in the Noometry coding category.

Which has the bigger context window?

Both accept 1.05M tokens.

How many benchmarks do Gemini 2.5 Flash and Gemini 3.1 Pro Preview share?

38 benchmarks have published results for both models. Gemini 2.5 Flash has 54 scored results on Noometry and Gemini 3.1 Pro Preview has 71.

Related comparisons

Go deeper