Noometry

Model comparison

Gemini 2.5 Flash vs Gemini 3 Flash Preview

Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 39.3 on the Noometry Index.

Last verified . 37 shared benchmarks.

Gemini 2.5 Flash Google

39.3

Rank #170 Confirmed

Gemini 3 Flash Preview Google

52.3

Rank #40 Confirmed

Summary

  • They share 37 benchmarks with published results for both. Gemini 2.5 Flash scores higher in 2 categories and Gemini 3 Flash Preview in 8 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Gemini 3 Flash Preview leads 49.2 to 18.1.
  • The biggest single-benchmark swing is ARC-AGI-1: 33.3% for Gemini 2.5 Flash and 84.7% for Gemini 3 Flash Preview.
  • Gemini 2.5 Flash is cheaper at $0.30 / $2.50 per million input/output tokens, against $0.50 / $3 for Gemini 3 Flash Preview.

Side by side

Gemini 2.5 FlashGemini 3 Flash Preview
ProviderGoogleGoogle
Noometry Index39.352.3
Released2025-04-172025-12-17
WeightsProprietaryProprietary
Context window1.05M1.05M
Max output66K66K
Input $ / M tokens$0.30$0.50
Output $ / M tokens$2.50$3
Results tracked5459

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

Category by category

Coding Gemini 3 Flash Preview leads

Gemini 2.5 Flash: 35.8 (#220), Gemini 3 Flash Preview: 50.9 (#42)

BenchmarkGemini 2.5 FlashGemini 3 Flash Preview
SWE-bench Verified (bash only)28.7%75.8%
WeirdML41.9%61.6%
LMArena Coding14241460
ALE-Bench661.881,367
SWE-bench Verified—75.4%
Aider Polyglot55.1%—
LMArena WebDev—1439
SWE-bench Multilingual—72.7%
GSO—9.8%

Agentic & Tool Use Gemini 3 Flash Preview leads

Gemini 2.5 Flash: 30.8 (#74), Gemini 3 Flash Preview: 38.7 (#29)

BenchmarkGemini 2.5 FlashGemini 3 Flash Preview
Terminal-Bench17.1%64.3%
BALROG33.5%48.1%
Vending-Bench 2548.843,635
Berkeley Function Calling Leaderboard56.2%—
TheAgentCompany41.1%—
τ²-bench Airline—82.5%
τ²-bench Banking—27.3%
τ²-bench Retail—76.8%
τ²-bench Telecom—91.2%
DeepResearch Bench—49.8%
GDP.pdf—10%
LMArena Search—1198

Reasoning Gemini 3 Flash Preview leads

Gemini 2.5 Flash: 18.1 (#286), Gemini 3 Flash Preview: 49.2 (#37)

BenchmarkGemini 2.5 FlashGemini 3 Flash Preview
ARC-AGI-22.5%33.6%
SimpleBench41.2%61.1%
ARC-AGI-133.3%84.7%
LMArena Hard Prompts14221465
DTBench76.5%89.1%
LMCA27.5%43.1%
Epoch Capabilities Index143.03151.8
ForecastBench60.658.5
Kagi LLM Benchmark56.8%—
NYT Connections (extended)—83.1%
CritPt1.1%—
Chess Puzzles—40%
EnigmaEval2.7%—
Mystery Game Puzzles—26%

Math Gemini 3 Flash Preview leads

Gemini 2.5 Flash: 39.9 (#98), Gemini 3 Flash Preview: 51.7 (#55)

BenchmarkGemini 2.5 FlashGemini 3 Flash Preview
OTIS Mock AIME 2024-202573.1%95.6%
LMArena Math14151473
FrontierMath (Feb 2025 set)4.8%35.6%
FrontierMath Tier 4 (v1)4.2%4.2%
FrontierMath (Tiers 1-3)—51.2%
FrontierMath Tier 4—17.1%
MathArena Final-Answer Competitions—67.6%
ProofBench—15%
Omni-MATH38.5%—

Knowledge Gemini 3 Flash Preview leads

Gemini 2.5 Flash: 36.4 (#168), Gemini 3 Flash Preview: 58.8 (#33)

BenchmarkGemini 2.5 FlashGemini 3 Flash Preview
Vectara Hallucination Rate7.8%13.5%
LMArena Expert14261462
GPQA Diamond—89.4%
Humanity's Last Exam12.1%—
SimpleQA Verified—66.8%
MMLU-Pro63.9%—
Confabulations16.8%—
GPQA (HELM)39%—

Multimodal Gemini 3 Flash Preview leads

Gemini 2.5 Flash: 41.8 (#32), Gemini 3 Flash Preview: 45.5 (#16)

BenchmarkGemini 2.5 FlashGemini 3 Flash Preview
LMArena Vision12531285
GeoBench76%88%
VPCT46.2%72.6%
Blueprint-Bench 2—0%
LMArena Document—1413
SpatialViz-Bench36.9%—

Multilingual Gemini 3 Flash Preview leads

Gemini 2.5 Flash: 52.3 (#88), Gemini 3 Flash Preview: 55.7 (#27)

BenchmarkGemini 2.5 FlashGemini 3 Flash Preview
LMArena Non-English14091458
LMArena Chinese14501511
LMArena French14331477
LMArena German14181497
LMArena Japanese14051489
LMArena Korean13851443
LMArena Russian14151480
LMArena Spanish14211469

Instruction Following Too close to call

Gemini 2.5 Flash: 75.7 (#54), Gemini 3 Flash Preview: 75.7 (#56)

BenchmarkGemini 2.5 FlashGemini 3 Flash Preview
LMArena Instruction Following14051437
IFEval89.8%—

Long Context Gemini 2.5 Flash leads

Gemini 2.5 Flash: 47.5 (#17), Gemini 3 Flash Preview: 44.4 (#67)

BenchmarkGemini 2.5 FlashGemini 3 Flash Preview
LMArena Longer Query14191452
Fiction.LiveBench77.8%—

Writing & Preference Gemini 3 Flash Preview leads

Gemini 2.5 Flash: 53.8 (#157), Gemini 3 Flash Preview: 65.5 (#45)

BenchmarkGemini 2.5 FlashGemini 3 Flash Preview
LMArena Text14171466
LMArena Creative Writing14001457
LMArena Multi-Turn14081471
Short-Story Creative Writing76.5%—
EQ-Bench Creative Writing1137—
WildBench81.7%—

Frequently asked questions

Is Gemini 2.5 Flash better than Gemini 3 Flash Preview?

Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 39.3 on the Noometry Index.

Which is cheaper, Gemini 2.5 Flash or Gemini 3 Flash 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 Flash Preview lists at $0.50 and $3.

Is Gemini 2.5 Flash or Gemini 3 Flash Preview better for coding?

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

37 benchmarks have published results for both models. Gemini 2.5 Flash has 54 scored results on Noometry and Gemini 3 Flash Preview has 59.

Related comparisons

Go deeper