LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Gemini 3.1 Flash Lite Preview vs Gemini 3.5 Flash

Updated October 21, 2026. 71 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Gemini 3.1 Flash Lite Preview Replace Gemini 3.5 Flash
Gemini 3.1 Flash Lite PreviewGoogle
Coding
8.1
Overall
15.6
Output $/M
$1.50
1
Gemini 3.5 FlashGoogle
Coding
42.8
Overall
33.6
Output $/M
$9.00
69
vs boards won of 71 shared, 1 tied

Decision reading

Pick Gemini 3.5 Flash for coding: it scores 42.8 on the Vibe Coding Index against 8.1 for Gemini 3.1 Flash Lite Preview.

Pick Gemini 3.1 Flash Lite Preview when output tokens cost 6.0x less, or when a solved task costs $0.18 against $1.21.

Model AGemini 3.1 Flash Lite PreviewGoogle8.1/1001 independent benchmark$0.18 per solved taskModel BGemini 3.5 FlashGoogle42.8/1001 independent benchmark$1.21 per solved task
Shared results
71
Gemini 3.1 Flash Lite Preview only
6
Gemini 3.5 Flash only
39
Like-for-like categories
8 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 3.1 Flash Lite Preview 8.1 from 1 benchmark, Gemini 3.5 Flash 42.8 from 1 benchmark.
Widest category
Agentic work, 32.2 points apart on average over 4 shared benchmarks.
Widest single gap
Excel Modeling Benchmark (Vals AI): Gemini 3.1 Flash Lite Preview 8.6% against Gemini 3.5 Flash 63.5%, 54.9 points apart on a 0 to 100 scale.
Output price
Gemini 3.1 Flash Lite Preview $1.50 against Gemini 3.5 Flash $9.00 per million output tokens, 6.0x 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 3.1 Flash Lite PreviewBarsGemini 3.5 FlashTies
Coding0121 tie
Intelligence01
Agentic work04
Reasoning07
Math02
Knowledge19
Web design08
General026
All shared boards1691 tie
CodingLike-for-likeFour of these boards feed the Vibe Coding Index012
Coding benchmarks for Gemini 3.1 Flash Lite Preview and Gemini 3.5 Flash
BenchmarkGemini 3.1 Flash Lite PreviewGemini 3.5 FlashLeader
LMArena WebDev12571499Gemini 3.5 Flash
AA Coding Index34.7Not measuredOnly Gemini 3.1 Flash Lite Preview measured
LiveCodeBench (Vals AI)80.1%87.6%Gemini 3.5 Flash
SWE-bench Verified (Vals AI)62.8%78.8%Gemini 3.5 Flash
Terminal-Bench 4 (Vals AI)Not measured6.1%Only Gemini 3.5 Flash measured
Vibe Code Bench (Vals AI)0.0%48.7%Gemini 3.5 Flash
Code migration (Vals AI)4.6%26.8%Gemini 3.5 Flash
ProgramBench (Vals AI)0.0%0.0%Tie
Terminal-Bench 2.1 (Vals AI)34.1%74.2%Gemini 3.5 Flash
SkillsBench (Vals AI)Not measured52.7%Only Gemini 3.5 Flash measured
SciCodeNot measured53.9%Only Gemini 3.5 Flash measured
Terminal-Bench Hard (Artificial Analysis run)Not measured46.2%Only Gemini 3.5 Flash measured
WeirdMLNot measured62.6%Only Gemini 3.5 Flash measured
ALE-Bench797.7911.0Gemini 3.5 Flash
LMArena Text: coding14001493Gemini 3.5 Flash
LMArena Text: software and IT14131494Gemini 3.5 Flash
LMArena WebDev: React12451495Gemini 3.5 Flash
LMArena WebDev: HTML12761522Gemini 3.5 Flash
LMArena WebDev: from an image13361504Gemini 3.5 Flash
Neither model has a result on the other 19 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for Gemini 3.1 Flash Lite Preview and Gemini 3.5 Flash
BenchmarkGemini 3.1 Flash Lite PreviewGemini 3.5 FlashLeader
AA Intelligence Index15.633.6Gemini 3.5 Flash
Epoch Capabilities IndexNot measured154.9Only Gemini 3.5 Flash measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index04
Agentic work benchmarks for Gemini 3.1 Flash Lite Preview and Gemini 3.5 Flash
BenchmarkGemini 3.1 Flash Lite PreviewGemini 3.5 FlashLeader
AA Agentic Index1.6Not measuredOnly Gemini 3.1 Flash Lite Preview measured
Design Arena: agents building web appsNot measured1202Only Gemini 3.5 Flash measured
Design Arena: agents building full-stack appsNot measured1197Only Gemini 3.5 Flash measured
Design Arena: agents building mobile appsNot measured1175Only Gemini 3.5 Flash measured
Design Arena: agents building Android appsNot measured1190Only Gemini 3.5 Flash measured
Design Arena: agents building Godot gamesNot measured1098Only Gemini 3.5 Flash measured
Design Arena: agents building gamesNot measured1180Only Gemini 3.5 Flash measured
Design Arena: HTML slidesNot measured1142Only Gemini 3.5 Flash measured
Design Arena: PowerPoint slidesNot measured1178Only Gemini 3.5 Flash measured
Finance Agent (Vals AI)30.0%57.9%Gemini 3.5 Flash
Tax Agent Bench (Vals AI)3.1%21.6%Gemini 3.5 Flash
Legal Research Bench (Vals AI)3.4%30.8%Gemini 3.5 Flash
Excel Modeling Benchmark (Vals AI)8.6%63.5%Gemini 3.5 Flash
Terminal-Bench-Science (Vals AI)Not measured5.7%Only Gemini 3.5 Flash measured
τ²-Bench TelecomNot measured95.6%Only Gemini 3.5 Flash measured
APEX-AgentsNot measured27.5%Only Gemini 3.5 Flash measured
Vending-Bench 2Not measured$5,396Only Gemini 3.5 Flash measured
Neither model has a result on the other 22 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index07
Reasoning benchmarks for Gemini 3.1 Flash Lite Preview and Gemini 3.5 Flash
BenchmarkGemini 3.1 Flash Lite PreviewGemini 3.5 FlashLeader
GPQA Diamond81.1%92.7%Gemini 3.5 Flash
MMMU Pro (Vals AI)82.5%88.3%Gemini 3.5 Flash
GPQA Diamond (Artificial Analysis run)Not measured92.2%Only Gemini 3.5 Flash measured
Humanity's Last Exam (Artificial Analysis run)Not measured42.7%Only Gemini 3.5 Flash measured
GPQA Diamond (Epoch AI run)Not measured92.8%Only Gemini 3.5 Flash measured
ARC-AGINot measured92.5%Only Gemini 3.5 Flash measured
ARC-AGI-2Not measured72.1%Only Gemini 3.5 Flash measured
SimpleBenchNot measured76.7%Only Gemini 3.5 Flash measured
Chess puzzlesNot measured45.0%Only Gemini 3.5 Flash measured
Mystery game puzzlesNot measured32.0%Only Gemini 3.5 Flash measured
EBR-benchNot measured4.8%Only Gemini 3.5 Flash measured
LMArena Text: hard prompts14071488Gemini 3.5 Flash
LMArena Text: expert13981495Gemini 3.5 Flash
LMArena Text: hard prompts in English14031483Gemini 3.5 Flash
LMArena Vision: diagrams12421323Gemini 3.5 Flash
LMArena Vision: homework12711330Gemini 3.5 Flash
Neither model has a result on the other 5 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index02
Math benchmarks for Gemini 3.1 Flash Lite Preview and Gemini 3.5 Flash
BenchmarkGemini 3.1 Flash Lite PreviewGemini 3.5 FlashLeader
AIME83.3%Not measuredOnly Gemini 3.1 Flash Lite Preview measured
OTIS Mock AIMENot measured95.6%Only Gemini 3.5 Flash measured
FrontierMath, tiers 1 to 3Not measured62.8%Only Gemini 3.5 Flash measured
FrontierMath, tier 4Not measured26.8%Only Gemini 3.5 Flash measured
ProofBenchNot measured31.0%Only Gemini 3.5 Flash measured
LMArena Text: math14281504Gemini 3.5 Flash
LMArena Text: mathematical work14171495Gemini 3.5 Flash
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index19
Knowledge benchmarks for Gemini 3.1 Flash Lite Preview and Gemini 3.5 Flash
BenchmarkGemini 3.1 Flash Lite PreviewGemini 3.5 FlashLeader
MMLU Pro86.2%89.5%Gemini 3.5 Flash
LegalBench (Vals AI)83.8%83.6%Gemini 3.1 Flash Lite Preview
CaseLaw (Vals AI)55.0%Not measuredOnly Gemini 3.1 Flash Lite Preview measured
CorpFin (Vals AI)59.4%64.7%Gemini 3.5 Flash
TaxEval (Vals AI)71.8%74.4%Gemini 3.5 Flash
MortgageTax (Vals AI)68.0%68.1%Gemini 3.5 Flash
MedCode (Vals AI)47.6%55.8%Gemini 3.5 Flash
SimpleQA VerifiedNot measured66.2%Only Gemini 3.5 Flash measured
LMArena Text: science14251495Gemini 3.5 Flash
LMArena Text: medicine and healthcare14281483Gemini 3.5 Flash
LMArena Text: legal and government14181488Gemini 3.5 Flash
LMArena Text: business and finance13891467Gemini 3.5 Flash
Neither model has a result on the other 5 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index08
Web design benchmarks for Gemini 3.1 Flash Lite Preview and Gemini 3.5 Flash
BenchmarkGemini 3.1 Flash Lite PreviewGemini 3.5 FlashLeader
Design Arena: websites10831268Gemini 3.5 Flash
Design Arena: UI components10711272Gemini 3.5 Flash
Design Arena: game dev10291263Gemini 3.5 Flash
Design Arena: data viz10451236Gemini 3.5 Flash
Design Arena: 3D10481244Gemini 3.5 Flash
Design Arena: all code categories10721266Gemini 3.5 Flash
Design Arena: SVG10521254Gemini 3.5 Flash
Design Arena: ASCII art11661253Gemini 3.5 Flash
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index026
General benchmarks for Gemini 3.1 Flash Lite Preview and Gemini 3.5 Flash
BenchmarkGemini 3.1 Flash Lite PreviewGemini 3.5 FlashLeader
Public Benefits Bench (Vals AI)Not measured59.5%Only Gemini 3.5 Flash measured
SAGE (Vals AI)49.5%49.9%Gemini 3.5 Flash
MedScribe (Vals AI)63.9%76.6%Gemini 3.5 Flash
Vals Multimodal Index41.4%62.9%Gemini 3.5 Flash
IFBenchNot measured76.3%Only Gemini 3.5 Flash measured
Long context reasoning (AA-LCR)Not measured74.3%Only Gemini 3.5 Flash measured
DTBenchNot measured94.7%Only Gemini 3.5 Flash measured
LMCANot measured47.1%Only Gemini 3.5 Flash measured
Surface Evolver BenchNot measured58.1%Only Gemini 3.5 Flash measured
LMArena Text14161482Gemini 3.5 Flash
LMArena Text: instruction following13771467Gemini 3.5 Flash
LMArena Text: creative writing14011470Gemini 3.5 Flash
LMArena Vision12401308Gemini 3.5 Flash
LMArena Text: English14141481Gemini 3.5 Flash
LMArena Text: non-English14101475Gemini 3.5 Flash
LMArena Text: Chinese14601527Gemini 3.5 Flash
LMArena Text: German14301494Gemini 3.5 Flash
LMArena Text: Japanese14131486Gemini 3.5 Flash
LMArena Text: Korean13921448Gemini 3.5 Flash
LMArena Text: French14241490Gemini 3.5 Flash
LMArena Text: Spanish14211480Gemini 3.5 Flash
LMArena Text: Russian14201493Gemini 3.5 Flash
LMArena Text: Polish14431516Gemini 3.5 Flash
LMArena Text: multi-turn14171481Gemini 3.5 Flash
LMArena Text: longer queries13941483Gemini 3.5 Flash
LMArena Text: writing and language14081478Gemini 3.5 Flash
LMArena Text: entertainment and media13861459Gemini 3.5 Flash
LMArena Vision: English12321305Gemini 3.5 Flash
LMArena Vision: Chinese12781377Gemini 3.5 Flash
LMArena Vision: reading text12461317Gemini 3.5 Flash
LMArena Vision: humor12661321Gemini 3.5 Flash
LMArena Vision: captioning1259Not measuredOnly Gemini 3.1 Flash Lite Preview measured
LMArena Vision: recognizing things1308Not measuredOnly Gemini 3.1 Flash Lite Preview measured
LMArena Vision: creative writing12481301Gemini 3.5 Flash
LMArena DocumentNot measured1463Only Gemini 3.5 Flash measured
Neither model has a result on the other 11 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Gemini 3.1 Flash Lite Preview and Gemini 3.5 Flash
BenchmarkGemini 3.1 Flash Lite PreviewGemini 3.5 FlashLeader
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 3.1 Flash Lite Preview$0.0010Fits in one request
Gemini 3.5 Flash$0.0060Fits in one request

Gemini 3.1 Flash Lite Preview costs less

Repository review

50K input + 3K output tokens

Gemini 3.1 Flash Lite Preview$0.017Fits in one request
Gemini 3.5 Flash$0.102Fits in one request

Gemini 3.1 Flash Lite Preview costs less

Agent loop

200K input + 10K output tokens

Gemini 3.1 Flash Lite Preview$0.065Fits in one request
Gemini 3.5 Flash$0.390Fits in one request

Gemini 3.1 Flash Lite Preview 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 3.1 Flash Lite Preview and Gemini 3.5 Flash
SpecificationGoogle Gemini 3.1 Flash Lite PreviewGoogle Gemini 3.5 Flash
MakerGoogleGoogle
WeightsNo public weights listedNo public weights listed
ReleasedMarch 3, 2026May 19, 2026
Context window1.05M1.05M
Input $/Mtok$0.25$1.50
Output $/Mtok$1.50$9.00
Coding index8.142.8
Independent measurements behind it11
Cost per solved task$0.18$1.21
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemini 3.1 Flash Lite Preview better than Gemini 3.5 Flash for coding?

Pick Gemini 3.5 Flash for coding: it scores 42.8 on the Vibe Coding Index against 8.1 for Gemini 3.1 Flash Lite Preview. Pick Gemini 3.1 Flash Lite Preview when output tokens cost 6.0x less, or when a solved task costs $0.18 against $1.21.

Which is cheaper, Gemini 3.1 Flash Lite Preview or Gemini 3.5 Flash?

Gemini 3.1 Flash Lite Preview costs $0.25 per million input tokens and $1.50 per million output tokens; Gemini 3.5 Flash costs $1.50 and $9.00. Per solved SWE-bench Verified task, Gemini 3.1 Flash Lite Preview costs $0.18 and Gemini 3.5 Flash $1.21.

Which has the bigger context window, Gemini 3.1 Flash Lite Preview or Gemini 3.5 Flash?

Neither: both take 1.05M tokens.

How many benchmarks is the Gemini 3.1 Flash Lite Preview vs Gemini 3.5 Flash comparison based on?

71 benchmarks have a result for both models as of October 21, 2026. Gemini 3.1 Flash Lite Preview's coding index rests on 1 independent benchmark and Gemini 3.5 Flash's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next