Noometry

Model comparison

Gemini 2.5 Flash vs Gemini 3.8 Flash

Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 39.3 on the Noometry Index. Gemini 2.5 Flash costs 1.8× less per token, which makes it the better buy when Gemini 3.8 Flash's lead doesn't matter for your workload.

Last verified . 30 shared benchmarks.

Gemini 2.5 Flash Google

39.3

Rank #170 Confirmed

Gemini 3.8 Flash Google

61.8

Rank #11 Confirmed

Summary

  • They share 30 benchmarks with published results for both. Gemini 2.5 Flash scores higher in 2 categories and Gemini 3.8 Flash in 8 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Gemini 3.8 Flash leads 76.9 to 18.1.
  • The biggest single-benchmark swing is ARC-AGI-2: 2.5% for Gemini 2.5 Flash and 89.2% for Gemini 3.8 Flash.
  • Gemini 2.5 Flash is cheaper at $0.30 / $2.50 per million input/output tokens, against $0.75 / $3.75 for Gemini 3.8 Flash.

Side by side

Gemini 2.5 FlashGemini 3.8 Flash
ProviderGoogleGoogle
Noometry Index39.361.8
Released2025-04-172026-09-02
WeightsProprietaryProprietary
Context window1.05M1.05M
Max output66K66K
Input $ / M tokens$0.30$0.75
Output $ / M tokens$2.50$3.75
Results tracked5450

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

Category by category

Coding Gemini 3.8 Flash leads

Gemini 2.5 Flash: 35.8 (#220), Gemini 3.8 Flash: 59.2 (#15)

BenchmarkGemini 2.5 FlashGemini 3.8 Flash
WeirdML41.9%84.8%
LMArena Coding14241510
ALE-Bench661.881,270
DeepSWE—73.8%
FrontierCode—41.2%
SWE-bench Verified (bash only)28.7%—
Aider Polyglot55.1%—
CursorBench—39.6%
LMArena WebDev—1584
FrontierSWE—19.6%
SciCode—56.6%

Agentic & Tool Use Gemini 3.8 Flash leads

Gemini 2.5 Flash: 30.8 (#74), Gemini 3.8 Flash: 41.8 (#21)

BenchmarkGemini 2.5 FlashGemini 3.8 Flash
Vending-Bench 2548.845,094
Terminal-Bench17.1%—
APEX-Agents—64.3%
Berkeley Function Calling Leaderboard56.2%—
Remote Labor Index—5.8%
TheAgentCompany41.1%—
BALROG33.5%—
GDP.pdf—23.4%

Reasoning Gemini 3.8 Flash leads

Gemini 2.5 Flash: 18.1 (#286), Gemini 3.8 Flash: 76.9 (#5)

BenchmarkGemini 2.5 FlashGemini 3.8 Flash
ARC-AGI-22.5%89.2%
ARC-AGI-133.3%98.5%
CritPt1.1%18.3%
LMArena Hard Prompts14221508
DTBench76.5%95.7%
LMCA27.5%52.9%
Epoch Capabilities Index143.03156.71
SimpleBench41.2%—
Kagi LLM Benchmark56.8%—
NYT Connections (extended)—97.4%
Chess Puzzles—61%
EnigmaEval2.7%—
Mystery Game Puzzles—47%
Surface Evolver Bench—76.9%
ForecastBench60.6—

Math Gemini 3.8 Flash leads

Gemini 2.5 Flash: 39.9 (#98), Gemini 3.8 Flash: 65.3 (#28)

BenchmarkGemini 2.5 FlashGemini 3.8 Flash
OTIS Mock AIME 2024-202573.1%98.9%
LMArena Math14151528
FrontierMath (Tiers 1-3)—68.4%
FrontierMath Tier 4—22%
ProofBench—48%
Omni-MATH38.5%—
FrontierMath (Feb 2025 set)4.8%—
FrontierMath Tier 4 (v1)4.2%—

Knowledge Gemini 3.8 Flash leads

Gemini 2.5 Flash: 36.4 (#168), Gemini 3.8 Flash: 74.8 (#2)

BenchmarkGemini 2.5 FlashGemini 3.8 Flash
Humanity's Last Exam12.1%44.5%
LMArena Expert14261524
GPQA Diamond—95.4%
SimpleQA Verified—69.7%
MMLU-Pro63.9%—
Confabulations16.8%—
Vectara Hallucination Rate7.8%—
GPQA (HELM)39%—

Multimodal Gemini 2.5 Flash leads

Gemini 2.5 Flash: 41.8 (#32), Gemini 3.8 Flash: 40.7 (#45)

BenchmarkGemini 2.5 FlashGemini 3.8 Flash
LMArena Vision12531314
GeoBench76%—
VPCT46.2%—
Blueprint-Bench 2—38.6%
Furniture Assembly—31.7%
SpatialViz-Bench36.9%—

Multilingual Gemini 3.8 Flash leads

Gemini 2.5 Flash: 52.3 (#88), Gemini 3.8 Flash: 58.0 (#5)

BenchmarkGemini 2.5 FlashGemini 3.8 Flash
LMArena Non-English14091491
LMArena Chinese14501554
LMArena French14331498
LMArena German14181493
LMArena Japanese14051502
LMArena Korean13851459
LMArena Russian14151515
LMArena Spanish14211485

Instruction Following Gemini 3.8 Flash leads

Gemini 2.5 Flash: 75.7 (#54), Gemini 3.8 Flash: 78.0 (#13)

BenchmarkGemini 2.5 FlashGemini 3.8 Flash
LMArena Instruction Following14051490
IFEval89.8%—

Long Context Gemini 2.5 Flash leads

Gemini 2.5 Flash: 47.5 (#17), Gemini 3.8 Flash: 46.3 (#24)

BenchmarkGemini 2.5 FlashGemini 3.8 Flash
LMArena Longer Query14191508
Fiction.LiveBench77.8%—

Writing & Preference Gemini 3.8 Flash leads

Gemini 2.5 Flash: 53.8 (#157), Gemini 3.8 Flash: 72.2 (#15)

BenchmarkGemini 2.5 FlashGemini 3.8 Flash
LMArena Text14171499
LMArena Creative Writing14001492
EQ-Bench Creative Writing11371748
LMArena Multi-Turn14081501
Short-Story Creative Writing76.5%—
WildBench81.7%—

Frequently asked questions

Is Gemini 2.5 Flash better than Gemini 3.8 Flash?

Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 39.3 on the Noometry Index. Gemini 2.5 Flash costs 1.8× less per token, which makes it the better buy when Gemini 3.8 Flash's lead doesn't matter for your workload.

Which is cheaper, Gemini 2.5 Flash or Gemini 3.8 Flash?

Gemini 2.5 Flash is cheaper. It lists at $0.30 per million input tokens and $2.50 per million output tokens; Gemini 3.8 Flash lists at $0.75 and $3.75.

Is Gemini 2.5 Flash or Gemini 3.8 Flash better for coding?

Gemini 3.8 Flash scores higher on coding benchmarks: 59.2 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 3.8 Flash share?

30 benchmarks have published results for both models. Gemini 2.5 Flash has 54 scored results on Noometry and Gemini 3.8 Flash has 50.

Related comparisons

Go deeper