Noometry

Model comparison

Gemini 2.5 Pro vs Gemini 3.5 Flash

Gemini 3.5 Flash is the stronger model overall, scoring 54.2 to 45.0 on the Noometry Index.

Last verified . 41 shared benchmarks.

Gemini 2.5 Pro Google

45.0

Rank #75 Confirmed

Gemini 3.5 Flash Google

54.2

Rank #32 Confirmed

Summary

  • They share 41 benchmarks with published results for both. Gemini 2.5 Pro scores higher in 2 categories and Gemini 3.5 Flash in 8 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Gemini 3.5 Flash leads 62.8 to 28.8.
  • The biggest single-benchmark swing is ARC-AGI-2: 4.9% for Gemini 2.5 Pro and 72.1% for Gemini 3.5 Flash.
  • Both cost about the same: $1.25 input and $10 output per million tokens.

Side by side

Gemini 2.5 ProGemini 3.5 Flash
ProviderGoogleGoogle
Noometry Index45.054.2
Released2025-03-252026-05-19
WeightsProprietaryProprietary
Context window1.05M1.05M
Max output66K66K
Input $ / M tokens$1.25$1.50
Output $ / M tokens$10$9
Results tracked7854

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

Category by category

Coding Gemini 3.5 Flash leads

Gemini 2.5 Pro: 42.4 (#101), Gemini 3.5 Flash: 49.4 (#49)

BenchmarkGemini 2.5 ProGemini 3.5 Flash
SWE-bench Verified57.6%79.3%
LMArena WebDev12271499
SciCode42.8%53.1%
WeirdML54%62.6%
LMArena Coding14521492
ALE-Bench785.52911.02
DeepSWE—37.4%
SWE-bench Verified (bash only)53.6%—
Aider Polyglot83.1%—
GSO3.9%—
LiveBench Coding85.9%—
CadEval64%—
AlgoTune1.51—

Agentic & Tool Use Gemini 2.5 Pro leads

Gemini 2.5 Pro: 29.2 (#88), Gemini 3.5 Flash: 24.7 (#114)

BenchmarkGemini 2.5 ProGemini 3.5 Flash
Vending-Bench 2573.645,396
Terminal-Bench32.6%—
APEX-Agents—27.5%
GDPval23.3%—
Remote Labor Index0.8%—
TheAgentCompany30.3%—
τ²-bench Banking13.7%—
DeepResearch Bench42.8%—
BALROG43.3%—
GBAEval—6.7%
GDP.pdf—14%
LMArena Search1142—
METR Time Horizons55.4%—

Reasoning Gemini 3.5 Flash leads

Gemini 2.5 Pro: 28.8 (#99), Gemini 3.5 Flash: 62.8 (#18)

BenchmarkGemini 2.5 ProGemini 3.5 Flash
ARC-AGI-24.9%72.1%
SimpleBench62.4%76.7%
ARC-AGI-141%92.5%
CritPt2%13.1%
Chess Puzzles20%50%
EnigmaEval5.6%25.4%
LMArena Hard Prompts14551488
DTBench82.4%94.7%
LMCA34.8%47.1%
Epoch Capabilities Index145.32154.46
ForecastBench61.359
Kagi LLM Benchmark70.3%—
NYT Connections (extended)—92.6%
EBR-Bench—4.8%
LiveBench Reasoning89.8%—
Mystery Game Puzzles—32%
LiveBench Data Analysis79.9%—
Surface Evolver Bench—58.1%
LiveBench82.3%—

Math Gemini 3.5 Flash leads

Gemini 2.5 Pro: 32.5 (#213), Gemini 3.5 Flash: 60.7 (#36)

BenchmarkGemini 2.5 ProGemini 3.5 Flash
FrontierMath (Tiers 1-3)24.6%62.8%
FrontierMath Tier 40%26.8%
OTIS Mock AIME 2024-202584.7%95.6%
LMArena Math14501504
FrontierMath (Feb 2025 set)14.1%39%
FrontierMath Tier 4 (v1)4.2%14.6%
MathArena Final-Answer Competitions—76.3%
ProofBench—31%
Omni-MATH41.6%—
LiveBench Math90.2%—
MATH Level 595.9%—

Knowledge Gemini 3.5 Flash leads

Gemini 2.5 Pro: 56.0 (#46), Gemini 3.5 Flash: 66.3 (#11)

BenchmarkGemini 2.5 ProGemini 3.5 Flash
GPQA Diamond85.3%92.8%
LMArena Expert14521495
Humanity's Last Exam21.6%—
SimpleQA Verified—66.2%
MMLU-Pro86.3%—
Confabulations10.6%—
Vectara Hallucination Rate7%—
GPQA (HELM)74.9%—

Multimodal Too close to call

Gemini 2.5 Pro: 45.2 (#18), Gemini 3.5 Flash: 45.7 (#15)

BenchmarkGemini 2.5 ProGemini 3.5 Flash
LMArena Vision12631310
LMArena Document14211463
GeoBench86%—
VPCT48%—
Blueprint-Bench 2—33.6%
SpatialViz-Bench44.7%—

Multilingual Gemini 3.5 Flash leads

Gemini 2.5 Pro: 55.3 (#31), Gemini 3.5 Flash: 57.0 (#13)

BenchmarkGemini 2.5 ProGemini 3.5 Flash
LMArena Non-English14511476
LMArena Chinese15071526
LMArena French14721490
LMArena German14871492
LMArena Japanese14611486
LMArena Korean14341451
LMArena Russian14611493
LMArena Spanish14731480

Instruction Following Gemini 3.5 Flash leads

Gemini 2.5 Pro: 75.0 (#75), Gemini 3.5 Flash: 77.0 (#30)

BenchmarkGemini 2.5 ProGemini 3.5 Flash
LMArena Instruction Following14371467
LiveBench Instruction Following80.6%—
IFEval84%—

Long Context Gemini 2.5 Pro leads

Gemini 2.5 Pro: 59.8 (#5), Gemini 3.5 Flash: 45.4 (#38)

BenchmarkGemini 2.5 ProGemini 3.5 Flash
LMArena Longer Query14491482
Fiction.LiveBench91.7%—

Writing & Preference Gemini 3.5 Flash leads

Gemini 2.5 Pro: 63.7 (#62), Gemini 3.5 Flash: 65.5 (#47)

BenchmarkGemini 2.5 ProGemini 3.5 Flash
LMArena Text14581482
LMArena Creative Writing14541470
LMArena Multi-Turn14531481
Short-Story Creative Writing83.8%—
EQ-Bench Creative Writing1421—
WildBench85.7%—
EQ-Bench 4—1087
LiveBench Language67.8%—

Frequently asked questions

Is Gemini 2.5 Pro better than Gemini 3.5 Flash?

Gemini 3.5 Flash is the stronger model overall, scoring 54.2 to 45.0 on the Noometry Index.

Which is cheaper, Gemini 2.5 Pro or Gemini 3.5 Flash?

Gemini 3.5 Flash is cheaper. It lists at $1.50 per million input tokens and $9 per million output tokens; Gemini 2.5 Pro lists at $1.25 and $10.

Is Gemini 2.5 Pro or Gemini 3.5 Flash better for coding?

Gemini 3.5 Flash scores higher on coding benchmarks: 49.4 versus 42.4 in the Noometry coding category.

Which has the bigger context window?

Both accept 1.05M tokens.

How many benchmarks do Gemini 2.5 Pro and Gemini 3.5 Flash share?

41 benchmarks have published results for both models. Gemini 2.5 Pro has 78 scored results on Noometry and Gemini 3.5 Flash has 54.

Related comparisons

Go deeper