Enter opens the highlighted result. Esc closes.

Gemini 3.5 Flash Lite vs GPT-5 Mini

Gemini 3.5 Flash Lite leads GPT-5 Mini on coding, 49.0 to 34.2 on the Vibe Coding Index, and GPT-5 Mini costs 1.3x less per output token ($2.00 vs $2.50 per million). Updated October 21, 2026; 68 benchmarks have a result for both.

Replace Gemini 3.5 Flash Lite Replace GPT-5 Mini
Gemini 3.5 Flash LiteGoogle
Coding
49.0
Overall
49.8
Output $/M
$2.50
57
GPT-5 MiniOpenAI
Coding
34.2
Overall
43.7
Output $/M
$2.00
11
vs boards won of 68 shared

Gemini 3.5 Flash Lite or GPT-5 Mini: which to pick

Pick Gemini 3.5 Flash Lite for coding: it scores 49.0 on the Vibe Coding Index against 34.2 for GPT-5 Mini.

Pick GPT-5 Mini for output tokens 1.3x cheaper ($2.00 vs $2.50 per million) and a lower cost per solved task ($0.08 against $0.41).

Model AGemini 3.5 Flash LiteGoogle49.0/1003 independent benchmarks$0.41 per solved taskModel BGPT-5 MiniOpenAI34.2/1002 independent benchmarks$0.08 per solved task
Shared results
68
Gemini 3.5 Flash Lite only
17
GPT-5 Mini only
33
Like-for-like categories
6 of 9

Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.

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 3.5 Flash Lite 49.0 from 3 benchmarks, GPT-5 Mini 34.2 from 2 benchmarks.
Widest category
Math, 11.8 points apart on average over 6 shared benchmarks.
Widest single gap
Vibe Code Bench (Vals AI): Gemini 3.5 Flash Lite 37.2% against GPT-5 Mini 14.2%, 23.0 points apart on a 0 to 100 scale.
Output price
Gemini 3.5 Flash Lite $2.50 against GPT-5 Mini $2.00 per million output tokens, 1.3x apart.
Context window
Gemini 3.5 Flash Lite takes 1.05M tokens, GPT-5 Mini 400K.

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 3.5 Flash LiteBarsGPT-5 MiniTies
Coding52
Intelligence11
Reasoning113
Math33
Knowledge101
General271
All shared boards5711
CodingLike-for-likeSix of these boards feed the Vibe Coding Index52
Coding benchmarks for Gemini 3.5 Flash Lite and GPT-5 Mini
BenchmarkGemini 3.5 Flash LiteGPT-5 MiniLeader
SWE-bench VerifiedNot measured59.8%Only GPT-5 Mini measured
SWE-bench MultilingualNot measured39.7%Only GPT-5 Mini measured
LMArena WebDev1435Not measuredOnly Gemini 3.5 Flash Lite measured
AA Coding Index49.3Not measuredOnly Gemini 3.5 Flash Lite measured
LiveCodeBench (Vals AI)79.0%86.6%GPT-5 Mini
SWE-bench Verified (Vals AI)75.0%60.8%Gemini 3.5 Flash Lite
Vibe Code Bench (Vals AI)37.2%14.2%Gemini 3.5 Flash Lite
Code migration (Vals AI)6.2%Not measuredOnly Gemini 3.5 Flash Lite measured
ProgramBench (Vals AI)0.0%Not measuredOnly Gemini 3.5 Flash Lite measured
Terminal-Bench 2.1 (Vals AI)50.2%Not measuredOnly Gemini 3.5 Flash Lite measured
CyberBench (Vals AI)59.1%Not measuredOnly Gemini 3.5 Flash Lite measured
LiveCodeBench (Artificial Analysis run)Not measured83.8%Only GPT-5 Mini measured
SciCode41.3%39.0%Gemini 3.5 Flash Lite
Terminal-Bench Hard (Artificial Analysis run)Not measured33.3%Only GPT-5 Mini measured
Terminal-BenchNot measured34.8%Only GPT-5 Mini measured
WeirdML39.0%52.7%GPT-5 Mini
ALE-Bench765.3Not measuredOnly Gemini 3.5 Flash Lite measured
LMArena Text: coding14531406Gemini 3.5 Flash Lite
LMArena Text: software and IT14511394Gemini 3.5 Flash Lite
LMArena WebDev: React1408Not measuredOnly Gemini 3.5 Flash Lite measured
LMArena WebDev: from an image1448Not measuredOnly Gemini 3.5 Flash Lite measured
SciCode6.2%Not measuredOnly Gemini 3.5 Flash Lite measured
Neither model has a result on the other 17 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index11
Intelligence benchmarks for Gemini 3.5 Flash Lite and GPT-5 Mini
BenchmarkGemini 3.5 Flash LiteGPT-5 MiniLeader
AA Intelligence Index22.220.6Gemini 3.5 Flash Lite
Epoch Capabilities Index144.9145.3GPT-5 Mini
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
Agentic work benchmarks for Gemini 3.5 Flash Lite and GPT-5 Mini
BenchmarkGemini 3.5 Flash LiteGPT-5 MiniLeader
AA Agentic Index14.3Not measuredOnly Gemini 3.5 Flash Lite measured
Finance Agent (Vals AI)47.4%Not measuredOnly Gemini 3.5 Flash Lite measured
Tax Agent Bench (Vals AI)7.2%Not measuredOnly Gemini 3.5 Flash Lite measured
Legal Research Bench (Vals AI)13.9%Not measuredOnly Gemini 3.5 Flash Lite measured
Excel Modeling Benchmark (Vals AI)43.2%Not measuredOnly Gemini 3.5 Flash Lite measured
τ²-Bench TelecomNot measured71.1%Only GPT-5 Mini measured
APEX-Agents29.3%Not measuredOnly Gemini 3.5 Flash Lite measured
Vending-Bench 2Not measured-$31Only GPT-5 Mini measured
Berkeley Function Calling Leaderboard (BFCL)Not measured55.5%Only GPT-5 Mini measured
Neither model has a result on the other 32 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index113
Reasoning benchmarks for Gemini 3.5 Flash Lite and GPT-5 Mini
BenchmarkGemini 3.5 Flash LiteGPT-5 MiniLeader
GPQA Diamond83.8%80.3%Gemini 3.5 Flash Lite
MMMU Pro (Vals AI)83.6%78.9%Gemini 3.5 Flash Lite
GPQA Diamond (Artificial Analysis run)83.8%82.8%Gemini 3.5 Flash Lite
Humanity's Last Exam (Artificial Analysis run)18.8%21.5%GPT-5 Mini
GPQA Diamond (Epoch AI run)83.3%75.0%Gemini 3.5 Flash Lite
ARC-AGI53.5%54.3%GPT-5 Mini
ARC-AGI-210.3%4.4%Gemini 3.5 Flash Lite
Chess puzzles21.0%24.0%GPT-5 Mini
Mystery game puzzles19.0%10.0%Gemini 3.5 Flash Lite
VPCTNot measured40.2%Only GPT-5 Mini measured
LMArena Text: hard prompts14411380Gemini 3.5 Flash Lite
LMArena Text: expert14341379Gemini 3.5 Flash Lite
LMArena Text: hard prompts in English14401383Gemini 3.5 Flash Lite
LMArena Vision: diagrams12841202Gemini 3.5 Flash Lite
LMArena Vision: homework12911210Gemini 3.5 Flash Lite
Kagi LLM BenchmarkNot measured70.3%Only GPT-5 Mini measured
Neither model has a result on the other 6 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index33
Math benchmarks for Gemini 3.5 Flash Lite and GPT-5 Mini
BenchmarkGemini 3.5 Flash LiteGPT-5 MiniLeader
AIMENot measured91.5%Only GPT-5 Mini measured
MATH 500 (Vals AI)Not measured94.8%Only GPT-5 Mini measured
MGSM (Vals AI)Not measured92.6%Only GPT-5 Mini measured
AA Math IndexNot measured90.7Only GPT-5 Mini measured
AIME 2025 (Artificial Analysis run)Not measured90.7%Only GPT-5 Mini measured
OTIS Mock AIME71.1%86.7%GPT-5 Mini
FrontierMath, tiers 1 to 326.0%46.7%GPT-5 Mini
FrontierMath, tier 40.0%12.2%GPT-5 Mini
ProofBench13.0%9.0%Gemini 3.5 Flash Lite
MATH level 5Not measured97.8%Only GPT-5 Mini measured
LMArena Text: math14341378Gemini 3.5 Flash Lite
LMArena Text: mathematical work14331380Gemini 3.5 Flash Lite
Neither model has a result on the other 1 board here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index101
Knowledge benchmarks for Gemini 3.5 Flash Lite and GPT-5 Mini
BenchmarkGemini 3.5 Flash LiteGPT-5 MiniLeader
MMLU Pro85.8%82.2%Gemini 3.5 Flash Lite
LegalBench (Vals AI)84.1%81.8%Gemini 3.5 Flash Lite
CaseLaw (Vals AI)Not measured68.5%Only GPT-5 Mini measured
CorpFin (Vals AI)60.7%60.2%Gemini 3.5 Flash Lite
TaxEval (Vals AI)72.6%75.2%GPT-5 Mini
MortgageTax (Vals AI)68.7%66.9%Gemini 3.5 Flash Lite
MedQA (Vals AI)Not measured96.1%Only GPT-5 Mini measured
MedCode (Vals AI)43.5%43.0%Gemini 3.5 Flash Lite
MMLU Pro (Artificial Analysis run)Not measured83.7%Only GPT-5 Mini measured
SimpleQA VerifiedNot measured21.6%Only GPT-5 Mini measured
LMArena Text: science14511371Gemini 3.5 Flash Lite
LMArena Text: medicine and healthcare14381380Gemini 3.5 Flash Lite
LMArena Text: legal and government14311375Gemini 3.5 Flash Lite
LMArena Text: business and finance14231358Gemini 3.5 Flash Lite
FACTS Benchmark Suite53.5%38.6%Gemini 3.5 Flash Lite
Neither model has a result on the other 3 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
Web design benchmarks for Gemini 3.5 Flash Lite and GPT-5 Mini
BenchmarkGemini 3.5 Flash LiteGPT-5 MiniLeader
Design Arena: websitesNot measured1125Only GPT-5 Mini measured
Design Arena: UI componentsNot measured1106Only GPT-5 Mini measured
Design Arena: game devNot measured1130Only GPT-5 Mini measured
Design Arena: data vizNot measured1130Only GPT-5 Mini measured
Design Arena: 3DNot measured1037Only GPT-5 Mini measured
Design Arena: all code categoriesNot measured1115Only GPT-5 Mini measured
Design Arena: SVGNot measured1091Only GPT-5 Mini measured
Design Arena: ASCII artNot measured1125Only GPT-5 Mini measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index271
General benchmarks for Gemini 3.5 Flash Lite and GPT-5 Mini
BenchmarkGemini 3.5 Flash LiteGPT-5 MiniLeader
Public Benefits Bench (Vals AI)51.8%Not measuredOnly Gemini 3.5 Flash Lite measured
SAGE (Vals AI)47.3%43.0%Gemini 3.5 Flash Lite
MedScribe (Vals AI)70.9%80.6%GPT-5 Mini
IFBenchNot measured75.4%Only GPT-5 Mini measured
Long context reasoning (AA-LCR)76.0%72.3%Gemini 3.5 Flash Lite
DTBench83.5%80.5%Gemini 3.5 Flash Lite
LMCA37.6%34.2%Gemini 3.5 Flash Lite
Fiction.LiveBenchNot measured69.4%Only GPT-5 Mini measured
Creative writing (Lech Mazur)Not measured83.1%Only GPT-5 Mini measured
LMArena Text14351373Gemini 3.5 Flash Lite
LMArena Text: instruction following14191357Gemini 3.5 Flash Lite
LMArena Text: creative writing14211325Gemini 3.5 Flash Lite
LMArena Vision12691202Gemini 3.5 Flash Lite
LMArena Text: English14381379Gemini 3.5 Flash Lite
LMArena Text: non-English14271363Gemini 3.5 Flash Lite
LMArena Text: Chinese14681386Gemini 3.5 Flash Lite
LMArena Text: German14541366Gemini 3.5 Flash Lite
LMArena Text: Japanese14261341Gemini 3.5 Flash Lite
LMArena Text: Korean14071308Gemini 3.5 Flash Lite
LMArena Text: French14511386Gemini 3.5 Flash Lite
LMArena Text: Spanish14411354Gemini 3.5 Flash Lite
LMArena Text: Russian14431362Gemini 3.5 Flash Lite
LMArena Text: Polish14371378Gemini 3.5 Flash Lite
LMArena Text: multi-turn14451363Gemini 3.5 Flash Lite
LMArena Text: longer queries14351355Gemini 3.5 Flash Lite
LMArena Text: writing and language14281344Gemini 3.5 Flash Lite
LMArena Text: entertainment and media14141340Gemini 3.5 Flash Lite
LMArena Vision: English12691216Gemini 3.5 Flash Lite
LMArena Vision: Chinese13111214Gemini 3.5 Flash Lite
LMArena Vision: reading text12801199Gemini 3.5 Flash Lite
LMArena Vision: humor12871205Gemini 3.5 Flash Lite
LMArena Vision: captioningNot measured1217Only GPT-5 Mini measured
LMArena Vision: recognizing thingsNot measured1226Only GPT-5 Mini measured
LMArena Vision: creative writing12601181Gemini 3.5 Flash Lite
Neither model has a result on the other 12 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Gemini 3.5 Flash Lite and GPT-5 Mini
BenchmarkGemini 3.5 Flash LiteGPT-5 MiniLeader
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 3.5 Flash Lite$0.0015Fits in one request
GPT-5 Mini$0.0013Fits in one request

GPT-5 Mini costs less

Repository review

50K input + 3K output tokens

Gemini 3.5 Flash Lite$0.022Fits in one request
GPT-5 Mini$0.018Fits in one request

GPT-5 Mini costs less

Agent loop

200K input + 10K output tokens

Gemini 3.5 Flash Lite$0.085Fits in one request
GPT-5 Mini$0.070Fits in one request

GPT-5 Mini 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 3.5 Flash Lite and GPT-5 Mini
SpecificationGoogle Gemini 3.5 Flash LiteOpenAI GPT-5 Mini
MakerGoogleOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedJuly 21, 2026August 7, 2025
Context window1.05M400K
Input $/Mtok$0.30$0.25
Output $/Mtok$2.50$2.00
Coding index49.034.2
Independent measurements behind it32
Cost per solved task$0.41$0.08
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemini 3.5 Flash Lite better than GPT-5 Mini for coding?

Pick Gemini 3.5 Flash Lite for coding: it scores 49.0 on the Vibe Coding Index against 34.2 for GPT-5 Mini. Pick GPT-5 Mini for output tokens 1.3x cheaper ($2.00 vs $2.50 per million) and a lower cost per solved task ($0.08 against $0.41).

Which is cheaper, Gemini 3.5 Flash Lite or GPT-5 Mini?

Gemini 3.5 Flash Lite costs $0.30 per million input tokens and $2.50 per million output tokens; GPT-5 Mini costs $0.25 and $2.00. Per solved SWE-bench Verified task, Gemini 3.5 Flash Lite costs $0.41 and GPT-5 Mini $0.08.

Which has the bigger context window, Gemini 3.5 Flash Lite or GPT-5 Mini?

Gemini 3.5 Flash Lite, with 1.05M tokens against 400K.

How many benchmarks is the Gemini 3.5 Flash Lite vs GPT-5 Mini comparison based on?

68 benchmarks have a result for both models as of October 21, 2026. Gemini 3.5 Flash Lite's coding index rests on 3 independent benchmarks and GPT-5 Mini's on 2. Where only one model has a result, the page says so instead of naming a winner.

Compare next

Embed this comparison on your site

Free under CC BY 4.0, while the source link stays visible. Preview the frame · Terms and other embeds

<iframe src="https://llmbenchmark.ai/embed/compare/gemini-3-5-flash-lite-vs-gpt-5-mini" title="Gemini 3.5 Flash Lite vs GPT-5 Mini, LLMBenchmark.ai" width="100%" height="360" style="border:0;max-width:100%" loading="lazy"></iframe>
<p style="font:13px/1.4 sans-serif;margin:6px 0 0">Source: <a href="https://llmbenchmark.ai/compare/gemini-3-5-flash-lite-vs-gpt-5-mini">LLMBenchmark.ai, Gemini 3.5 Flash Lite vs GPT-5 Mini</a></p>