LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Gemini 3.1 Flash Lite Preview vs Gemini 3.7 Flash

Updated October 21, 2026. 70 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 3.7 Flash
Gemini 3.1 Flash Lite PreviewGoogle
Coding
8.1
Overall
15.6
Output $/M
$1.50
2
Gemini 3.7 FlashGoogle
Coding
69.9
Overall
39.6
Output $/M
$3.75
67
vs boards won of 70 shared, 1 tied

Decision reading

Pick Gemini 3.7 Flash for coding: it scores 69.9 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 2.5x less, or when a solved task costs $0.18 against $1.78.

Model AGemini 3.1 Flash Lite PreviewGoogle8.1/1001 independent benchmark$0.18 per solved taskModel BGemini 3.7 FlashGoogle69.9/1002 independent benchmarks$1.78 per solved task
Shared results
70
Gemini 3.1 Flash Lite Preview only
7
Gemini 3.7 Flash only
42
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 3.7 Flash 69.9 from 2 benchmarks.
Widest category
Agentic work, 35.7 points apart on average over 4 shared benchmarks.
Widest single gap
Vibe Code Bench (Vals AI): Gemini 3.1 Flash Lite Preview 0.0% against Gemini 3.7 Flash 70.4%, 70.4 points apart on a 0 to 100 scale.
Output price
Gemini 3.1 Flash Lite Preview $1.50 against Gemini 3.7 Flash $3.75 per million output tokens, 2.5x 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 3.1 Flash Lite PreviewBarsGemini 3.7 FlashTies
Coding0131 tie
Intelligence01
Agentic work04
Reasoning07
Math02
Knowledge18
Web design08
General124
All shared boards2671 tie
CodingLike-for-likeFour of these boards feed the Vibe Coding Index013
Coding benchmarks for Gemini 3.1 Flash Lite Preview and Gemini 3.7 Flash
BenchmarkGemini 3.1 Flash Lite PreviewGemini 3.7 FlashLeader
LiveBench codingNot measured80.5%Only Gemini 3.7 Flash measured
LMArena WebDev12571591Gemini 3.7 Flash
AA Coding Index34.771.5Gemini 3.7 Flash
LiveCodeBench (Vals AI)80.1%88.7%Gemini 3.7 Flash
SWE-bench Verified (Vals AI)62.8%80.8%Gemini 3.7 Flash
Terminal-Bench 4 (Vals AI)Not measured12.1%Only Gemini 3.7 Flash measured
Vibe Code Bench (Vals AI)0.0%70.4%Gemini 3.7 Flash
Code migration (Vals AI)4.6%34.8%Gemini 3.7 Flash
ProgramBench (Vals AI)0.0%0.0%Tie
IOI (Vals AI)Not measured67.8%Only Gemini 3.7 Flash measured
Terminal-Bench 2.1 (Vals AI)34.1%77.5%Gemini 3.7 Flash
SkillsBench (Vals AI)Not measured65.9%Only Gemini 3.7 Flash measured
CyberBench (Vals AI)Not measured43.8%Only Gemini 3.7 Flash measured
SciCodeNot measured59.8%Only Gemini 3.7 Flash measured
FrontierCodeNot measured43.6%Only Gemini 3.7 Flash measured
FrontierSWENot measured20.3%Only Gemini 3.7 Flash measured
ALE-Bench797.7904.3Gemini 3.7 Flash
LMArena Text: coding14001499Gemini 3.7 Flash
LMArena Text: software and IT14131498Gemini 3.7 Flash
LMArena WebDev: React12451587Gemini 3.7 Flash
LMArena WebDev: HTML12761593Gemini 3.7 Flash
LMArena WebDev: from an image13361599Gemini 3.7 Flash
Neither model has a result on the other 16 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 3.7 Flash
BenchmarkGemini 3.1 Flash Lite PreviewGemini 3.7 FlashLeader
AA Intelligence Index15.639.6Gemini 3.7 Flash
Epoch Capabilities IndexNot measured158.0Only Gemini 3.7 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 3.7 Flash
BenchmarkGemini 3.1 Flash Lite PreviewGemini 3.7 FlashLeader
AA Agentic Index1.6Not measuredOnly Gemini 3.1 Flash Lite Preview measured
Design Arena: agents building web appsNot measured1224Only Gemini 3.7 Flash measured
Design Arena: agents building full-stack appsNot measured1208Only Gemini 3.7 Flash measured
Design Arena: agents building mobile appsNot measured1230Only Gemini 3.7 Flash measured
Design Arena: agents building Android appsNot measured1247Only Gemini 3.7 Flash measured
Design Arena: agents building Godot gamesNot measured1264Only Gemini 3.7 Flash measured
Design Arena: agents building gamesNot measured1235Only Gemini 3.7 Flash measured
Design Arena: spreadsheetsNot measured1028Only Gemini 3.7 Flash measured
LiveBench researchNot measured76.5%Only Gemini 3.7 Flash measured
LiveBench browserNot measured56.0%Only Gemini 3.7 Flash measured
LiveBench long agenticNot measured28.3%Only Gemini 3.7 Flash measured
SREBench (Vals AI)Not measured4.6%Only Gemini 3.7 Flash measured
Finance Agent (Vals AI)30.0%59.0%Gemini 3.7 Flash
Tax Agent Bench (Vals AI)3.1%22.8%Gemini 3.7 Flash
Legal Research Bench (Vals AI)3.4%34.6%Gemini 3.7 Flash
Excel Modeling Benchmark (Vals AI)8.6%71.3%Gemini 3.7 Flash
Terminal-Bench-Science (Vals AI)Not measured7.1%Only Gemini 3.7 Flash measured
APEX-AgentsNot measured67.8%Only Gemini 3.7 Flash measured
Remote Labor IndexNot measured5.0%Only Gemini 3.7 Flash measured
Neither model has a result on the other 20 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 3.7 Flash
BenchmarkGemini 3.1 Flash Lite PreviewGemini 3.7 FlashLeader
GPQA Diamond81.1%93.9%Gemini 3.7 Flash
LiveBench reasoningNot measured87.8%Only Gemini 3.7 Flash measured
MMMU Pro (Vals AI)82.5%89.0%Gemini 3.7 Flash
GPQA Diamond (Artificial Analysis run)Not measured94.5%Only Gemini 3.7 Flash measured
Humanity's Last Exam (Artificial Analysis run)Not measured47.9%Only Gemini 3.7 Flash measured
GPQA Diamond (Epoch AI run)Not measured94.8%Only Gemini 3.7 Flash measured
ARC-AGINot measured95.5%Only Gemini 3.7 Flash measured
ARC-AGI-2Not measured84.6%Only Gemini 3.7 Flash measured
Chess puzzlesNot measured66.0%Only Gemini 3.7 Flash measured
Mystery game puzzlesNot measured37.0%Only Gemini 3.7 Flash measured
LMArena Text: hard prompts14071495Gemini 3.7 Flash
LMArena Text: expert13981512Gemini 3.7 Flash
LMArena Text: hard prompts in English14031487Gemini 3.7 Flash
LMArena Vision: diagrams12421329Gemini 3.7 Flash
LMArena Vision: homework12711320Gemini 3.7 Flash
Neither model has a result on the other 6 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 3.7 Flash
BenchmarkGemini 3.1 Flash Lite PreviewGemini 3.7 FlashLeader
AIME83.3%Not measuredOnly Gemini 3.1 Flash Lite Preview measured
OTIS Mock AIMENot measured97.2%Only Gemini 3.7 Flash measured
FrontierMath, tiers 1 to 3Not measured71.6%Only Gemini 3.7 Flash measured
FrontierMath, tier 4Not measured36.6%Only Gemini 3.7 Flash measured
ProofBenchNot measured58.0%Only Gemini 3.7 Flash measured
LMArena Text: math14281511Gemini 3.7 Flash
LMArena Text: mathematical work14171502Gemini 3.7 Flash
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index18
Knowledge benchmarks for Gemini 3.1 Flash Lite Preview and Gemini 3.7 Flash
BenchmarkGemini 3.1 Flash Lite PreviewGemini 3.7 FlashLeader
MMLU Pro86.2%90.1%Gemini 3.7 Flash
LegalBench (Vals AI)83.8%87.3%Gemini 3.7 Flash
CaseLaw (Vals AI)55.0%Not measuredOnly Gemini 3.1 Flash Lite Preview measured
CorpFin (Vals AI)59.4%Not measuredOnly Gemini 3.1 Flash Lite Preview measured
TaxEval (Vals AI)71.8%74.7%Gemini 3.7 Flash
MortgageTax (Vals AI)68.0%66.7%Gemini 3.1 Flash Lite Preview
MedCode (Vals AI)47.6%53.4%Gemini 3.7 Flash
SimpleQA VerifiedNot measured69.2%Only Gemini 3.7 Flash measured
LMArena Text: science14251511Gemini 3.7 Flash
LMArena Text: medicine and healthcare14281494Gemini 3.7 Flash
LMArena Text: legal and government14181496Gemini 3.7 Flash
LMArena Text: business and finance13891479Gemini 3.7 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 3.7 Flash
BenchmarkGemini 3.1 Flash Lite PreviewGemini 3.7 FlashLeader
Design Arena: websites10831304Gemini 3.7 Flash
Design Arena: UI components10711299Gemini 3.7 Flash
Design Arena: game dev10291318Gemini 3.7 Flash
Design Arena: data viz10451315Gemini 3.7 Flash
Design Arena: 3D10481308Gemini 3.7 Flash
Design Arena: all code categories10721308Gemini 3.7 Flash
Design Arena: SVG10521283Gemini 3.7 Flash
Design Arena: ASCII art11661276Gemini 3.7 Flash
LiveBench designNot measured73.2%Only Gemini 3.7 Flash measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index124
General benchmarks for Gemini 3.1 Flash Lite Preview and Gemini 3.7 Flash
BenchmarkGemini 3.1 Flash Lite PreviewGemini 3.7 FlashLeader
LiveBench data analysisNot measured68.0%Only Gemini 3.7 Flash measured
SAGE (Vals AI)49.5%49.2%Gemini 3.1 Flash Lite Preview
MedScribe (Vals AI)63.9%83.9%Gemini 3.7 Flash
Vals Multimodal Index41.4%Not measuredOnly Gemini 3.1 Flash Lite Preview measured
Long context reasoning (AA-LCR)Not measured83.0%Only Gemini 3.7 Flash measured
DTBenchNot measured96.8%Only Gemini 3.7 Flash measured
LMCANot measured50.4%Only Gemini 3.7 Flash measured
Furniture assemblyNot measured26.7%Only Gemini 3.7 Flash measured
LMArena Text14161489Gemini 3.7 Flash
LMArena Text: instruction following13771484Gemini 3.7 Flash
LMArena Text: creative writing14011488Gemini 3.7 Flash
LMArena Vision12401314Gemini 3.7 Flash
LMArena Text: English14141483Gemini 3.7 Flash
LMArena Text: non-English14101487Gemini 3.7 Flash
LMArena Text: Chinese14601552Gemini 3.7 Flash
LMArena Text: German14301506Gemini 3.7 Flash
LMArena Text: Japanese14131511Gemini 3.7 Flash
LMArena Text: Korean13921481Gemini 3.7 Flash
LMArena Text: French14241500Gemini 3.7 Flash
LMArena Text: Spanish14211495Gemini 3.7 Flash
LMArena Text: Russian14201515Gemini 3.7 Flash
LMArena Text: Polish14431503Gemini 3.7 Flash
LMArena Text: multi-turn14171485Gemini 3.7 Flash
LMArena Text: longer queries13941492Gemini 3.7 Flash
LMArena Text: writing and language14081491Gemini 3.7 Flash
LMArena Text: entertainment and media13861477Gemini 3.7 Flash
LMArena Vision: English12321309Gemini 3.7 Flash
LMArena Vision: Chinese12781394Gemini 3.7 Flash
LMArena Vision: reading text12461322Gemini 3.7 Flash
LMArena Vision: humor12661299Gemini 3.7 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 writing12481312Gemini 3.7 Flash
Neither model has a result on the other 13 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 3.7 Flash
BenchmarkGemini 3.1 Flash Lite PreviewGemini 3.7 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 3.7 Flash$0.0026Fits 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 3.7 Flash$0.049Fits 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 3.7 Flash$0.188Fits 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 3.7 Flash
SpecificationGoogle Gemini 3.1 Flash Lite PreviewGoogle Gemini 3.7 Flash
MakerGoogleGoogle
WeightsNo public weights listedNo public weights listed
ReleasedMarch 3, 2026August 13, 2026
Context window1.05M1.05M
Input $/Mtok$0.25$0.75
Output $/Mtok$1.50$3.75
Coding index8.169.9
Independent measurements behind it12
Cost per solved task$0.18$1.78
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemini 3.1 Flash Lite Preview better than Gemini 3.7 Flash for coding?

Pick Gemini 3.7 Flash for coding: it scores 69.9 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 2.5x less, or when a solved task costs $0.18 against $1.78.

Which is cheaper, Gemini 3.1 Flash Lite Preview or Gemini 3.7 Flash?

Gemini 3.1 Flash Lite Preview costs $0.25 per million input tokens and $1.50 per million output tokens; Gemini 3.7 Flash costs $0.75 and $3.75. Per solved SWE-bench Verified task, Gemini 3.1 Flash Lite Preview costs $0.18 and Gemini 3.7 Flash $1.78.

Which has the bigger context window, Gemini 3.1 Flash Lite Preview or Gemini 3.7 Flash?

Neither: both take 1.05M tokens.

How many benchmarks is the Gemini 3.1 Flash Lite Preview vs Gemini 3.7 Flash comparison based on?

70 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 3.7 Flash's on 2. Where only one model has a result, the page says so instead of naming a winner.

Compare next