Enter opens the highlighted result. Esc closes.

GPT-5 Mini vs o3 Mini

GPT-5 Mini leads o3 Mini on the Artificial Analysis Intelligence Index, 20.6 to 12.5, and GPT-5 Mini costs 2.2x less per output token ($2.00 vs $4.40 per million). Updated October 22, 2026; 65 benchmarks have a result for both.

Replace GPT-5 Mini Replace o3 Mini
GPT-5 MiniOpenAI
Coding
34.2
Overall
43.7
Output $/M
$2.00
60
o3 MiniOpenAI
Coding
No data
Overall
38.0
Output $/M
$4.40
5
vs boards won of 65 shared

GPT-5 Mini or o3 Mini: which to pick

Only GPT-5 Mini has a coding score, 34.2 on the Vibe Coding Index; o3 Mini has none, so the two cannot be ranked on coding.

Pick o3 Mini for work measured by SciCode or GPQA Diamond (Epoch AI run), where it leads.

Model AGPT-5 MiniOpenAI34.2/1002 independent benchmarks$0.08 per solved taskModel Bo3 MiniOpenAINot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
65
GPT-5 Mini only
36
o3 Mini only
6
Like-for-like categories
7 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 Mini 34.2 from 2 benchmarks, o3 Mini not benchmarked.
Widest category
Agentic work, 39.8 points apart on average over 1 shared benchmark.
Widest single gap
τ²-Bench Telecom: GPT-5 Mini 71.1% against o3 Mini 31.3%, 39.8 points apart on a 0 to 100 scale.
Output price
GPT-5 Mini $2.00 against o3 Mini $4.40 per million output tokens, 2.2x apart.
Context window
GPT-5 Mini takes 400K tokens, o3 Mini 200K.

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-5 MiniBarso3 MiniTies
Coding71
Intelligence20
Agentic work10
Reasoning101
Math72
Knowledge110
General221
All shared boards605
CodingLike-for-likeSix of these boards feed the Vibe Coding Index71
Coding benchmarks for GPT-5 Mini and o3 Mini
BenchmarkGPT-5 Minio3 MiniLeader
Aider polyglotNot measured60.4%Only o3 Mini measured
SWE-bench Verified59.8%42.4%GPT-5 Mini
SWE-bench LiteNot measured32.3%Only o3 Mini measured
SWE-bench Multilingual39.7%Not measuredOnly GPT-5 Mini measured
LiveCodeBench (Vals AI)86.6%71.5%GPT-5 Mini
SWE-bench Verified (Vals AI)60.8%Not measuredOnly GPT-5 Mini measured
Vibe Code Bench (Vals AI)14.2%Not measuredOnly GPT-5 Mini measured
LiveCodeBench (Artificial Analysis run)83.8%73.4%GPT-5 Mini
SciCode39.0%42.8%o3 Mini
Terminal-Bench Hard (Artificial Analysis run)33.3%6.8%GPT-5 Mini
Terminal-Bench34.8%Not measuredOnly GPT-5 Mini measured
GSO-BenchNot measured1.3%Only o3 Mini measured
WeirdML52.7%43.7%GPT-5 Mini
CybenchNot measured22.5%Only o3 Mini measured
LMArena Text: coding14061378GPT-5 Mini
LMArena Text: software and IT13941364GPT-5 Mini
SciCodeNot measured7.7%Only o3 Mini measured
Neither model has a result on the other 22 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for GPT-5 Mini and o3 Mini
BenchmarkGPT-5 Minio3 MiniLeader
AA Intelligence Index20.612.5GPT-5 Mini
Epoch Capabilities Index145.3140.2GPT-5 Mini
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for GPT-5 Mini and o3 Mini
BenchmarkGPT-5 Minio3 MiniLeader
τ²-Bench Telecom71.1%31.3%GPT-5 Mini
Vending-Bench 2-$31Not measuredOnly GPT-5 Mini measured
Berkeley Function Calling Leaderboard (BFCL)55.5%Not measuredOnly GPT-5 Mini measured
Neither model has a result on the other 38 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index101
Reasoning benchmarks for GPT-5 Mini and o3 Mini
BenchmarkGPT-5 Minio3 MiniLeader
GPQA Diamond80.3%75.5%GPT-5 Mini
MMMU Pro (Vals AI)78.9%Not measuredOnly GPT-5 Mini measured
GPQA Diamond (Artificial Analysis run)82.8%77.3%GPT-5 Mini
Humanity's Last Exam (Artificial Analysis run)21.5%12.0%GPT-5 Mini
GPQA Diamond (Epoch AI run)75.0%77.0%o3 Mini
ARC-AGI54.3%34.5%GPT-5 Mini
ARC-AGI-24.4%3.0%GPT-5 Mini
SimpleBenchNot measured22.8%Only o3 Mini measured
Chess puzzles24.0%15.0%GPT-5 Mini
Mystery game puzzles10.0%7.0%GPT-5 Mini
VPCT40.2%Not measuredOnly GPT-5 Mini measured
LMArena Text: hard prompts13801365GPT-5 Mini
LMArena Text: expert13791364GPT-5 Mini
LMArena Text: hard prompts in English13831375GPT-5 Mini
LMArena Vision: diagrams1202Not measuredOnly GPT-5 Mini measured
LMArena Vision: homework1210Not measuredOnly GPT-5 Mini measured
Kagi LLM Benchmark70.3%Not measuredOnly GPT-5 Mini measured
Neither model has a result on the other 5 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index72
Math benchmarks for GPT-5 Mini and o3 Mini
BenchmarkGPT-5 Minio3 MiniLeader
AIME91.5%86.5%GPT-5 Mini
MATH 500 (Vals AI)94.8%91.8%GPT-5 Mini
MGSM (Vals AI)92.6%91.3%GPT-5 Mini
AA Math Index90.7Not measuredOnly GPT-5 Mini measured
AIME 2025 (Artificial Analysis run)90.7%Not measuredOnly GPT-5 Mini measured
OTIS Mock AIME86.7%76.9%GPT-5 Mini
FrontierMath, tiers 1 to 346.7%18.6%GPT-5 Mini
FrontierMath, tier 412.2%0.0%GPT-5 Mini
ProofBench9.0%Not measuredOnly GPT-5 Mini measured
MATH level 597.8%96.5%GPT-5 Mini
LMArena Text: math13781396o3 Mini
LMArena Text: mathematical work13801399o3 Mini
Neither model has a result on the other 1 board here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index110
Knowledge benchmarks for GPT-5 Mini and o3 Mini
BenchmarkGPT-5 Minio3 MiniLeader
MMLU Pro82.2%78.7%GPT-5 Mini
LegalBench (Vals AI)81.8%71.5%GPT-5 Mini
CaseLaw (Vals AI)68.5%Not measuredOnly GPT-5 Mini measured
CorpFin (Vals AI)60.2%45.3%GPT-5 Mini
TaxEval (Vals AI)75.2%69.4%GPT-5 Mini
MortgageTax (Vals AI)66.9%Not measuredOnly GPT-5 Mini measured
MedQA (Vals AI)96.1%94.8%GPT-5 Mini
MedCode (Vals AI)43.0%Not measuredOnly GPT-5 Mini measured
MMLU Pro (Artificial Analysis run)83.7%80.2%GPT-5 Mini
SimpleQA Verified21.6%15.3%GPT-5 Mini
LMArena Text: science13711339GPT-5 Mini
LMArena Text: medicine and healthcare13801330GPT-5 Mini
LMArena Text: legal and government13751328GPT-5 Mini
LMArena Text: business and finance13581313GPT-5 Mini
FACTS Benchmark Suite38.6%Not measuredOnly GPT-5 Mini measured
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 GPT-5 Mini and o3 Mini
BenchmarkGPT-5 Minio3 MiniLeader
Design Arena: websites1125Not measuredOnly GPT-5 Mini measured
Design Arena: UI components1103Not measuredOnly GPT-5 Mini measured
Design Arena: game dev1129Not measuredOnly GPT-5 Mini measured
Design Arena: data viz1131Not measuredOnly GPT-5 Mini measured
Design Arena: 3D1036Not measuredOnly GPT-5 Mini measured
Design Arena: all code categories1114Not measuredOnly GPT-5 Mini measured
Design Arena: SVG1091Not measuredOnly GPT-5 Mini measured
Design Arena: ASCII art1125Not measuredOnly 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 index221
General benchmarks for GPT-5 Mini and o3 Mini
BenchmarkGPT-5 Minio3 MiniLeader
SAGE (Vals AI)43.0%Not measuredOnly GPT-5 Mini measured
MedScribe (Vals AI)80.6%Not measuredOnly GPT-5 Mini measured
IFBench75.4%67.1%GPT-5 Mini
Long context reasoning (AA-LCR)72.3%43.0%GPT-5 Mini
DTBench80.5%68.8%GPT-5 Mini
LMCA34.2%19.0%GPT-5 Mini
Fiction.LiveBench69.4%50.0%GPT-5 Mini
Creative writing (Lech Mazur)83.1%61.7%GPT-5 Mini
LMArena Text13731337GPT-5 Mini
LMArena Text: instruction following13571337GPT-5 Mini
LMArena Text: creative writing13251286GPT-5 Mini
LMArena Vision1202Not measuredOnly GPT-5 Mini measured
LMArena Text: English13791351GPT-5 Mini
LMArena Text: non-English13631319GPT-5 Mini
LMArena Text: Chinese13861379GPT-5 Mini
LMArena Text: German13661303GPT-5 Mini
LMArena Text: Japanese13411286GPT-5 Mini
LMArena Text: Korean13081313o3 Mini
LMArena Text: French13861334GPT-5 Mini
LMArena Text: Spanish13541321GPT-5 Mini
LMArena Text: Russian13621304GPT-5 Mini
LMArena Text: Polish13781294GPT-5 Mini
LMArena Text: multi-turn13631320GPT-5 Mini
LMArena Text: longer queries13551343GPT-5 Mini
LMArena Text: writing and language13441313GPT-5 Mini
LMArena Text: entertainment and media13401283GPT-5 Mini
LMArena Vision: English1216Not measuredOnly GPT-5 Mini measured
LMArena Vision: Chinese1214Not measuredOnly GPT-5 Mini measured
LMArena Vision: reading text1199Not measuredOnly GPT-5 Mini measured
LMArena Vision: humor1205Not measuredOnly GPT-5 Mini measured
LMArena Vision: captioning1217Not measuredOnly GPT-5 Mini measured
LMArena Vision: recognizing things1226Not measuredOnly GPT-5 Mini measured
LMArena Vision: creative writing1181Not measuredOnly GPT-5 Mini measured
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 Mini and o3 Mini
BenchmarkGPT-5 Minio3 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 Mini$0.0013Fits in one request
o3 Mini$0.0033Fits in one request

GPT-5 Mini costs less

Repository review

50K input + 3K output tokens

GPT-5 Mini$0.018Fits in one request
o3 Mini$0.068Fits in one request

GPT-5 Mini costs less

Agent loop

200K input + 10K output tokens

GPT-5 Mini$0.070Fits in one request
o3 Mini$0.264Exceeds the context window

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 Mini and o3 Mini
SpecificationOpenAI GPT-5 MiniOpenAI o3 Mini
MakerOpenAIOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedAugust 7, 2025January 31, 2025
Context window400K200K
Input $/Mtok$0.25$1.10
Output $/Mtok$2.00$4.40
Coding index34.2Not benchmarked
Independent measurements behind it20
Cost per solved task$0.08Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-5 Mini better than o3 Mini for coding?

Only GPT-5 Mini has a coding score, 34.2 on the Vibe Coding Index; o3 Mini has none, so the two cannot be ranked on coding. Pick o3 Mini for work measured by SciCode or GPQA Diamond (Epoch AI run), where it leads.

Which is cheaper, GPT-5 Mini or o3 Mini?

GPT-5 Mini costs $0.25 per million input tokens and $2.00 per million output tokens; o3 Mini costs $1.10 and $4.40. Cost per solved task is known for GPT-5 Mini only.

Which has the bigger context window, GPT-5 Mini or o3 Mini?

GPT-5 Mini, with 400K tokens against 200K.

How many benchmarks is the GPT-5 Mini vs o3 Mini comparison based on?

65 benchmarks have a result for both models as of October 22, 2026. GPT-5 Mini's coding index rests on 2 independent benchmarks and o3 Mini's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next