Enter opens the highlighted result. Esc closes.

GPT-5 vs GPT-5 Mini

GPT-5 leads GPT-5 Mini on coding, 38.8 to 34.2 on the Vibe Coding Index, and GPT-5 Mini costs 5.0x less per output token ($2.00 vs $10.00 per million). Updated October 21, 2026; 97 benchmarks have a result for both.

Replace GPT-5 Replace GPT-5 Mini
GPT-5OpenAI
Coding
38.8
Overall
51.5
Output $/M
$10.00
91
GPT-5 MiniOpenAI
Coding
34.2
Overall
43.7
Output $/M
$2.00
6
vs boards won of 97 shared

GPT-5 or GPT-5 Mini: which to pick

Pick GPT-5 for coding: it scores 38.8 on the Vibe Coding Index against 34.2 for GPT-5 Mini.

Pick GPT-5 Mini for output tokens 5.0x cheaper ($2.00 vs $10.00 per million) and a lower cost per solved task ($0.08 against $0.39).

Model AGPT-5OpenAI38.8/1003 independent benchmarks$0.39 per solved taskModel BGPT-5 MiniOpenAI34.2/1002 independent benchmarks$0.08 per solved task
Shared results
97
GPT-5 only
16
GPT-5 Mini only
4
Like-for-like categories
8 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
GPT-5 38.8 from 3 benchmarks, GPT-5 Mini 34.2 from 2 benchmarks.
Widest category
Agentic work, 15.5 points apart on average over 1 shared benchmark.
Widest single gap
SimpleQA Verified: GPT-5 50.1% against GPT-5 Mini 21.6%, 28.5 points apart on a 0 to 100 scale.
Output price
GPT-5 $10.00 against GPT-5 Mini $2.00 per million output tokens, 5.0x apart.
Context window
Both take 400K 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
CategoryGPT-5BarsGPT-5 MiniTies
Coding91
Intelligence20
Agentic work10
Reasoning160
Math120
Knowledge123
Web design80
General312
All shared boards916
CodingLike-for-likeSix of these boards feed the Vibe Coding Index91
Coding benchmarks for GPT-5 and GPT-5 Mini
BenchmarkGPT-5GPT-5 MiniLeader
Aider polyglot88.0%Not measuredOnly GPT-5 measured
SWE-bench Verified74.4%59.8%GPT-5
SWE-bench MultilingualNot measured39.7%Only GPT-5 Mini measured
LMArena WebDev1418Not measuredOnly GPT-5 measured
AA Coding Index37.8Not measuredOnly GPT-5 measured
LiveCodeBench (Vals AI)85.9%86.6%GPT-5 Mini
SWE-bench Verified (Vals AI)69.0%60.8%GPT-5
Vibe Code Bench (Vals AI)20.1%14.2%GPT-5
LiveCodeBench (Artificial Analysis run)84.6%83.8%GPT-5
SciCodeNot measured39.0%Only GPT-5 Mini measured
Terminal-Bench Hard (Artificial Analysis run)37.9%33.3%GPT-5
Terminal-Bench49.6%34.8%GPT-5
GSO-Bench6.9%Not measuredOnly GPT-5 measured
WeirdML60.7%52.7%GPT-5
ALE-Bench807.6Not measuredOnly GPT-5 measured
LMArena Text: coding14361406GPT-5
LMArena Text: software and IT14201394GPT-5
LMArena WebDev: HTML1427Not measuredOnly GPT-5 measured
SciCode0.0%Not measuredOnly GPT-5 measured
Neither model has a result on the other 20 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for GPT-5 and GPT-5 Mini
BenchmarkGPT-5GPT-5 MiniLeader
AA Intelligence Index23.020.6GPT-5
Epoch Capabilities Index150.0145.3GPT-5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for GPT-5 and GPT-5 Mini
BenchmarkGPT-5GPT-5 MiniLeader
τ²-Bench Telecom86.5%71.1%GPT-5
METR time horizons69.6%Not measuredOnly GPT-5 measured
Remote Labor Index1.7%Not measuredOnly GPT-5 measured
GDPval34.8%Not measuredOnly GPT-5 measured
BALROG32.8%Not measuredOnly GPT-5 measured
DeepResearch Bench49.6%Not measuredOnly GPT-5 measured
Vending-Bench 2Not measured-$31Only GPT-5 Mini measured
Berkeley Function Calling Leaderboard (BFCL)Not measured55.5%Only GPT-5 Mini measured
BrowseComp-Plus80.0%Not measuredOnly GPT-5 measured
Neither model has a result on the other 32 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index160
Reasoning benchmarks for GPT-5 and GPT-5 Mini
BenchmarkGPT-5GPT-5 MiniLeader
GPQA Diamond85.6%80.3%GPT-5
MMMU Pro (Vals AI)81.5%78.9%GPT-5
GPQA Diamond (Artificial Analysis run)85.4%82.8%GPT-5
Humanity's Last Exam (Artificial Analysis run)28.5%21.5%GPT-5
GPQA Diamond (Epoch AI run)86.2%75.0%GPT-5
ARC-AGI65.7%54.3%GPT-5
ARC-AGI-29.9%4.4%GPT-5
SimpleBench56.7%Not measuredOnly GPT-5 measured
Chess puzzles36.0%24.0%GPT-5
Mystery game puzzles23.0%10.0%GPT-5
EBR-bench12.7%Not measuredOnly GPT-5 measured
VPCT66.0%40.2%GPT-5
LMArena Text: hard prompts14151380GPT-5
LMArena Text: expert14191379GPT-5
LMArena Text: hard prompts in English14191383GPT-5
LMArena Vision: diagrams12521202GPT-5
LMArena Vision: homework12781210GPT-5
Kagi LLM Benchmark72.7%70.3%GPT-5
Neither model has a result on the other 4 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index120
Math benchmarks for GPT-5 and GPT-5 Mini
BenchmarkGPT-5GPT-5 MiniLeader
AIME93.4%91.5%GPT-5
MATH 500 (Vals AI)96.0%94.8%GPT-5
MGSM (Vals AI)92.8%92.6%GPT-5
AA Math Index94.390.7GPT-5
AIME 2025 (Artificial Analysis run)94.3%90.7%GPT-5
OTIS Mock AIME91.4%86.7%GPT-5
FrontierMath, tiers 1 to 355.4%46.7%GPT-5
FrontierMath, tier 422.0%12.2%GPT-5
ProofBench18.0%9.0%GPT-5
MATH level 598.1%97.8%GPT-5
LMArena Text: math14071378GPT-5
LMArena Text: mathematical work14051380GPT-5
Neither model has a result on the other 1 board here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index123
Knowledge benchmarks for GPT-5 and GPT-5 Mini
BenchmarkGPT-5GPT-5 MiniLeader
MMLU Pro86.5%82.2%GPT-5
LegalBench (Vals AI)86.0%81.8%GPT-5
CaseLaw (Vals AI)66.5%68.5%GPT-5 Mini
CorpFin (Vals AI)61.1%60.2%GPT-5
TaxEval (Vals AI)73.4%75.2%GPT-5 Mini
MortgageTax (Vals AI)65.5%66.9%GPT-5 Mini
MedQA (Vals AI)96.3%96.1%GPT-5
MedCode (Vals AI)49.6%43.0%GPT-5
MMLU Pro (Artificial Analysis run)87.1%83.7%GPT-5
SimpleQA Verified50.1%21.6%GPT-5
GeoBench81.0%Not measuredOnly GPT-5 measured
LMArena Text: science14161371GPT-5
LMArena Text: medicine and healthcare14131380GPT-5
LMArena Text: legal and government14311375GPT-5
LMArena Text: business and finance14001358GPT-5
FACTS Benchmark Suite56.5%38.6%GPT-5
Neither model has a result on the other 2 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index80
Web design benchmarks for GPT-5 and GPT-5 Mini
BenchmarkGPT-5GPT-5 MiniLeader
Design Arena: websites11841125GPT-5
Design Arena: UI components11801106GPT-5
Design Arena: game dev11851130GPT-5
Design Arena: data viz12211130GPT-5
Design Arena: 3D10561037GPT-5
Design Arena: all code categories11681115GPT-5
Design Arena: SVG11891091GPT-5
Design Arena: ASCII art11411125GPT-5
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index312
General benchmarks for GPT-5 and GPT-5 Mini
BenchmarkGPT-5GPT-5 MiniLeader
SAGE (Vals AI)43.7%43.0%GPT-5
MedScribe (Vals AI)83.7%80.6%GPT-5
IFBench73.1%75.4%GPT-5 Mini
Long context reasoning (AA-LCR)78.2%72.3%GPT-5
DTBench90.7%80.5%GPT-5
LMCA40.0%34.2%GPT-5
Fiction.LiveBench97.2%69.4%GPT-5
Creative writing (Lech Mazur)86.0%83.1%GPT-5
LMArena Text14061373GPT-5
LMArena Text: instruction following13881357GPT-5
LMArena Text: creative writing13651325GPT-5
LMArena Vision12321202GPT-5
LMArena Text: English14091379GPT-5
LMArena Text: non-English13971363GPT-5
LMArena Text: Chinese14221386GPT-5
LMArena Text: German14161366GPT-5
LMArena Text: Japanese14091341GPT-5
LMArena Text: Korean13601308GPT-5
LMArena Text: French14091386GPT-5
LMArena Text: Spanish13991354GPT-5
LMArena Text: Russian14071362GPT-5
LMArena Text: Polish14311378GPT-5
LMArena Text: multi-turn14261363GPT-5
LMArena Text: longer queries13991355GPT-5
LMArena Text: writing and language13841344GPT-5
LMArena Text: entertainment and media13791340GPT-5
LMArena Vision: English12311216GPT-5
LMArena Vision: Chinese12671214GPT-5
LMArena Vision: reading text12461199GPT-5
LMArena Vision: humor12191205GPT-5
LMArena Vision: captioning12121217GPT-5 Mini
LMArena Vision: recognizing things12631226GPT-5
LMArena Vision: creative writing12101181GPT-5
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 GPT-5 and GPT-5 Mini
BenchmarkGPT-5GPT-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

GPT-5$0.0063Fits in one request
GPT-5 Mini$0.0013Fits in one request

GPT-5 Mini costs less

Repository review

50K input + 3K output tokens

GPT-5$0.092Fits in one request
GPT-5 Mini$0.018Fits in one request

GPT-5 Mini costs less

Agent loop

200K input + 10K output tokens

GPT-5$0.350Fits 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 GPT-5 and GPT-5 Mini
SpecificationOpenAI GPT-5OpenAI GPT-5 Mini
MakerOpenAIOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedAugust 7, 2025August 7, 2025
Context window400K400K
Input $/Mtok$1.25$0.25
Output $/Mtok$10.00$2.00
Coding index38.834.2
Independent measurements behind it32
Cost per solved task$0.39$0.08
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-5 better than GPT-5 Mini for coding?

Pick GPT-5 for coding: it scores 38.8 on the Vibe Coding Index against 34.2 for GPT-5 Mini. Pick GPT-5 Mini for output tokens 5.0x cheaper ($2.00 vs $10.00 per million) and a lower cost per solved task ($0.08 against $0.39).

Which is cheaper, GPT-5 or GPT-5 Mini?

GPT-5 costs $1.25 per million input tokens and $10.00 per million output tokens; GPT-5 Mini costs $0.25 and $2.00. Per solved SWE-bench Verified task, GPT-5 costs $0.39 and GPT-5 Mini $0.08.

Which has the bigger context window, GPT-5 or GPT-5 Mini?

Neither: both take 400K tokens.

How many benchmarks is the GPT-5 vs GPT-5 Mini comparison based on?

97 benchmarks have a result for both models as of October 21, 2026. GPT-5'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/gpt-5-vs-gpt-5-mini" title="GPT-5 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/gpt-5-vs-gpt-5-mini">LLMBenchmark.ai, GPT-5 vs GPT-5 Mini</a></p>