Enter opens the highlighted result. Esc closes.

Gemini 2.5 Flash Lite vs Gemini 3 Flash Preview

Updated October 21, 2026. 27 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Gemini 2.5 Flash Lite Replace Gemini 3 Flash Preview
Gemini 2.5 Flash LiteGoogle
Coding
No data
Overall
10.4
Output $/M
$0.40
1
Gemini 3 Flash PreviewGoogle
Coding
43.7
Overall
26.3
Output $/M
$3.00
26
vs boards won of 27 shared

Decision reading

Only Gemini 3 Flash Preview has a coding score, 43.7 on the Vibe Coding Index; Gemini 2.5 Flash Lite has none, so the two cannot be ranked on coding.

Gemini 2.5 Flash Lite has the edge where output tokens cost 7.5x less, and where the benchmark that matters is MedScribe (Vals AI), where it leads.

Model AGemini 2.5 Flash LiteGoogleNot benchmarkedNo coding benchmarkNo cost per solved taskModel BGemini 3 Flash PreviewGoogle43.7/1002 independent benchmarks$0.37 per solved task
Shared results
27
Gemini 2.5 Flash Lite only
1
Gemini 3 Flash Preview only
42
Like-for-like categories
7 of 9

Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.

Which one for your work

Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.

At a glance

Coding index
Gemini 2.5 Flash Lite not benchmarked, Gemini 3 Flash Preview 43.7 from 2 benchmarks.
Widest category
Agentic work, 61.4 points apart on average over 1 shared benchmark.
Widest single gap
τ²-Bench Telecom: Gemini 2.5 Flash Lite 19.0% against Gemini 3 Flash Preview 80.4%, 61.4 points apart on a 0 to 100 scale.
Output price
Gemini 2.5 Flash Lite $0.40 against Gemini 3 Flash Preview $3.00 per million output tokens, 7.5x apart.
Context window
Both take 1.05M tokens.

Benchmark by benchmark

First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.

Boards won, where both have a result
CategoryGemini 2.5 Flash LiteBarsGemini 3 Flash PreviewTies
Coding03
Intelligence01
Agentic work01
Reasoning04
Math04
Knowledge08
General15
All shared boards126
CodingLike-for-likeSix of these boards feed the Vibe Coding Index03
Coding benchmarks for Gemini 2.5 Flash Lite and Gemini 3 Flash Preview
BenchmarkGemini 2.5 Flash LiteGemini 3 Flash PreviewLeader
SWE-bench VerifiedNot measured75.8%Only Gemini 3 Flash Preview measured
LiveCodeBench (Vals AI)71.4%85.6%Gemini 3 Flash Preview
SWE-bench Verified (Vals AI)Not measured75.0%Only Gemini 3 Flash Preview measured
Vibe Code Bench (Vals AI)Not measured20.2%Only Gemini 3 Flash Preview measured
Code migration (Vals AI)Not measured6.4%Only Gemini 3 Flash Preview measured
ProgramBench (Vals AI)Not measured0.0%Only Gemini 3 Flash Preview measured
Terminal-Bench 2.1 (Vals AI)Not measured53.9%Only Gemini 3 Flash Preview measured
LiveCodeBench (Artificial Analysis run)59.3%90.8%Gemini 3 Flash Preview
Terminal-Bench Hard (Artificial Analysis run)4.5%38.6%Gemini 3 Flash Preview
Terminal-BenchNot measured64.3%Only Gemini 3 Flash Preview measured
GSO-BenchNot measured9.8%Only Gemini 3 Flash Preview measured
WeirdMLNot measured61.6%Only Gemini 3 Flash Preview measured
ALE-BenchNot measured1367.2Only Gemini 3 Flash Preview measured
Neither model has a result on the other 25 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for Gemini 2.5 Flash Lite and Gemini 3 Flash Preview
BenchmarkGemini 2.5 Flash LiteGemini 3 Flash PreviewLeader
AA Intelligence Index10.426.3Gemini 3 Flash Preview
Epoch Capabilities Index133.8Not measuredOnly Gemini 2.5 Flash Lite measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for Gemini 2.5 Flash Lite and Gemini 3 Flash Preview
BenchmarkGemini 2.5 Flash LiteGemini 3 Flash PreviewLeader
Design Arena: agents building web appsNot measured1110Only Gemini 3 Flash Preview measured
Design Arena: agents building full-stack appsNot measured1063Only Gemini 3 Flash Preview measured
Design Arena: agents building mobile appsNot measured1090Only Gemini 3 Flash Preview measured
Design Arena: agents building Android appsNot measured1057Only Gemini 3 Flash Preview measured
Design Arena: agents building Godot gamesNot measured1161Only Gemini 3 Flash Preview measured
Design Arena: PowerPoint slidesNot measured1036Only Gemini 3 Flash Preview measured
Finance Agent (Vals AI)Not measured42.5%Only Gemini 3 Flash Preview measured
Tax Agent Bench (Vals AI)Not measured11.8%Only Gemini 3 Flash Preview measured
Legal Research Bench (Vals AI)Not measured18.3%Only Gemini 3 Flash Preview measured
Excel Modeling Benchmark (Vals AI)Not measured26.0%Only Gemini 3 Flash Preview measured
τ²-Bench Telecom19.0%80.4%Gemini 3 Flash Preview
BALROGNot measured48.1%Only Gemini 3 Flash Preview measured
DeepResearch BenchNot measured49.8%Only Gemini 3 Flash Preview measured
Vending-Bench 2Not measured$3,635Only Gemini 3 Flash Preview measured
Neither model has a result on the other 25 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index04
Reasoning benchmarks for Gemini 2.5 Flash Lite and Gemini 3 Flash Preview
BenchmarkGemini 2.5 Flash LiteGemini 3 Flash PreviewLeader
GPQA Diamond70.2%87.9%Gemini 3 Flash Preview
MMMU Pro (Vals AI)75.4%87.6%Gemini 3 Flash Preview
GPQA Diamond (Artificial Analysis run)62.5%89.8%Gemini 3 Flash Preview
Humanity's Last Exam (Artificial Analysis run)6.8%36.6%Gemini 3 Flash Preview
GPQA Diamond (Epoch AI run)Not measured89.4%Only Gemini 3 Flash Preview measured
ARC-AGINot measured84.7%Only Gemini 3 Flash Preview measured
ARC-AGI-2Not measured33.6%Only Gemini 3 Flash Preview measured
SimpleBenchNot measured61.1%Only Gemini 3 Flash Preview measured
Chess puzzlesNot measured39.0%Only Gemini 3 Flash Preview measured
Mystery game puzzlesNot measured26.0%Only Gemini 3 Flash Preview measured
VPCTNot measured72.6%Only Gemini 3 Flash Preview measured
Neither model has a result on the other 10 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index04
Math benchmarks for Gemini 2.5 Flash Lite and Gemini 3 Flash Preview
BenchmarkGemini 2.5 Flash LiteGemini 3 Flash PreviewLeader
AIME42.1%95.6%Gemini 3 Flash Preview
MGSM (Vals AI)89.5%93.3%Gemini 3 Flash Preview
AA Math Index53.397.0Gemini 3 Flash Preview
AIME 2025 (Artificial Analysis run)53.3%97.0%Gemini 3 Flash Preview
OTIS Mock AIMENot measured95.6%Only Gemini 3 Flash Preview measured
FrontierMath, tiers 1 to 3Not measured51.2%Only Gemini 3 Flash Preview measured
FrontierMath, tier 4Not measured17.1%Only Gemini 3 Flash Preview measured
ProofBenchNot measured15.0%Only Gemini 3 Flash Preview measured
Neither model has a result on the other 5 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index08
Knowledge benchmarks for Gemini 2.5 Flash Lite and Gemini 3 Flash Preview
BenchmarkGemini 2.5 Flash LiteGemini 3 Flash PreviewLeader
MMLU Pro79.1%88.6%Gemini 3 Flash Preview
LegalBench (Vals AI)82.0%86.9%Gemini 3 Flash Preview
CaseLaw (Vals AI)Not measured55.8%Only Gemini 3 Flash Preview measured
CorpFin (Vals AI)57.6%66.4%Gemini 3 Flash Preview
TaxEval (Vals AI)66.2%73.9%Gemini 3 Flash Preview
MortgageTax (Vals AI)57.6%68.7%Gemini 3 Flash Preview
MedQA (Vals AI)88.9%95.8%Gemini 3 Flash Preview
MedCode (Vals AI)34.2%55.9%Gemini 3 Flash Preview
MMLU Pro (Artificial Analysis run)75.9%89.0%Gemini 3 Flash Preview
SimpleQA VerifiedNot measured66.8%Only Gemini 3 Flash Preview measured
GeoBenchNot measured88.0%Only Gemini 3 Flash Preview measured
Neither model has a result on the other 6 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
Web design benchmarks for Gemini 2.5 Flash Lite and Gemini 3 Flash Preview
BenchmarkGemini 2.5 Flash LiteGemini 3 Flash PreviewLeader
Design Arena: websitesNot measured1196Only Gemini 3 Flash Preview measured
Design Arena: game devNot measured1166Only Gemini 3 Flash Preview measured
Design Arena: 3DNot measured1184Only Gemini 3 Flash Preview measured
Design Arena: all code categoriesNot measured1189Only Gemini 3 Flash Preview measured
Neither model has a result on the other 5 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index15
General benchmarks for Gemini 2.5 Flash Lite and Gemini 3 Flash Preview
BenchmarkGemini 2.5 Flash LiteGemini 3 Flash PreviewLeader
SAGE (Vals AI)30.8%51.8%Gemini 3 Flash Preview
MedScribe (Vals AI)75.8%69.9%Gemini 2.5 Flash Lite
Vals Multimodal IndexNot measured52.2%Only Gemini 3 Flash Preview measured
IFBench49.9%78.0%Gemini 3 Flash Preview
Long context reasoning (AA-LCR)55.7%78.0%Gemini 3 Flash Preview
DTBench62.8%89.1%Gemini 3 Flash Preview
LMCA18.1%43.1%Gemini 3 Flash Preview
Neither model has a result on the other 39 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Gemini 2.5 Flash Lite and Gemini 3 Flash Preview
BenchmarkGemini 2.5 Flash LiteGemini 3 Flash PreviewLeader
Neither model has a result on 5 boards here

What each workload costs

Three fixed token mixes at each model's listed price, so per-token rates become a bill.

Chat turn

1K input + 500 output tokens

Gemini 2.5 Flash Lite$0.0003Fits in one request
Gemini 3 Flash Preview$0.0020Fits in one request

Gemini 2.5 Flash Lite costs less

Repository review

50K input + 3K output tokens

Gemini 2.5 Flash Lite$0.0062Fits in one request
Gemini 3 Flash Preview$0.034Fits in one request

Gemini 2.5 Flash Lite costs less

Agent loop

200K input + 10K output tokens

Gemini 2.5 Flash Lite$0.024Fits in one request
Gemini 3 Flash Preview$0.130Fits in one request

Gemini 2.5 Flash Lite costs less

Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.

Specification differences

The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.

Specifications of Gemini 2.5 Flash Lite and Gemini 3 Flash Preview
SpecificationGoogle Gemini 2.5 Flash LiteGoogle Gemini 3 Flash Preview
MakerGoogleGoogle
WeightsNo public weights listedNo public weights listed
ReleasedJuly 22, 2025December 17, 2025
Context window1.05M1.05M
Input $/Mtok$0.10$0.50
Output $/Mtok$0.40$3.00
Coding indexNot benchmarked43.7
Independent measurements behind it02
Cost per solved taskNot computable$0.37
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemini 2.5 Flash Lite better than Gemini 3 Flash Preview for coding?

Only Gemini 3 Flash Preview has a coding score, 43.7 on the Vibe Coding Index; Gemini 2.5 Flash Lite has none, so the two cannot be ranked on coding. Gemini 2.5 Flash Lite has the edge where output tokens cost 7.5x less, and where the benchmark that matters is MedScribe (Vals AI), where it leads.

Which is cheaper, Gemini 2.5 Flash Lite or Gemini 3 Flash Preview?

Gemini 2.5 Flash Lite costs $0.10 per million input tokens and $0.40 per million output tokens; Gemini 3 Flash Preview costs $0.50 and $3.00. Cost per solved task is known for Gemini 3 Flash Preview only.

Which has the bigger context window, Gemini 2.5 Flash Lite or Gemini 3 Flash Preview?

Neither: both take 1.05M tokens.

How many benchmarks is the Gemini 2.5 Flash Lite vs Gemini 3 Flash Preview comparison based on?

27 benchmarks have a result for both models as of October 21, 2026. Gemini 2.5 Flash Lite's coding index rests on 0 independent benchmarks and Gemini 3 Flash Preview's on 2. Where only one model has a result, the page says so instead of naming a winner.

Compare next