LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

GPT-5.4 Mini vs o3

Updated October 21, 2026. 67 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace GPT-5.4 Mini Replace o3
GPT-5.4 MiniOpenAI
Coding
28.2
Overall
24.1
Output $/M
$4.50
47
o3OpenAI
Coding
70.7
Overall
20.2
Output $/M
$8.00
20
vs boards won of 67 shared

Decision reading

Pick o3 for coding: it scores 70.7 on the Vibe Coding Index against 28.2 for GPT-5.4 Mini.

Pick GPT-5.4 Mini when output tokens cost 1.8x less, or when the context window is larger, 400K against 200K tokens.

Model AGPT-5.4 MiniOpenAI28.2/1001 independent benchmark$0.70 per solved taskModel Bo3OpenAI70.7/1002 independent benchmarks$0.571 per solved task
Shared results
67
GPT-5.4 Mini only
21
o3 only
30
Like-for-like categories
7 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
GPT-5.4 Mini 28.2 from 1 benchmark, o3 70.7 from 2 benchmarks.
Widest category
Coding, 7.1 points apart on average over 6 shared benchmarks.
Widest single gap
SimpleQA Verified: GPT-5.4 Mini 29.4% against o3 49.4%, 20.0 points apart on a 0 to 100 scale.
Output price
GPT-5.4 Mini $4.50 against o3 $8.00 per million output tokens, 1.8x apart.
Context window
GPT-5.4 Mini takes 400K tokens, o3 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-5.4 MiniBarso3Ties
Coding51
Intelligence20
Agentic work11
Reasoning104
Math41
Knowledge27
General236
All shared boards4720
CodingLike-for-likeFour of these boards feed the Vibe Coding Index51
Coding benchmarks for GPT-5.4 Mini and o3
BenchmarkGPT-5.4 Minio3Leader
Aider polyglotNot measured81.3%Only o3 measured
SWE-bench VerifiedNot measured58.4%Only o3 measured
SWE-bench MultimodalNot measured36.0%Only o3 measured
LMArena WebDev1397Not measuredOnly GPT-5.4 Mini measured
AA Coding Index56.1Not measuredOnly GPT-5.4 Mini measured
LiveCodeBench (Vals AI)81.5%83.9%o3
SWE-bench Verified (Vals AI)73.0%Not measuredOnly GPT-5.4 Mini measured
Terminal-Bench 4 (Vals AI)2.5%Not measuredOnly GPT-5.4 Mini measured
Vibe Code Bench (Vals AI)48.0%Not measuredOnly GPT-5.4 Mini measured
Code migration (Vals AI)12.9%Not measuredOnly GPT-5.4 Mini measured
ProgramBench (Vals AI)0.0%Not measuredOnly GPT-5.4 Mini measured
Terminal-Bench 2.1 (Vals AI)54.7%Not measuredOnly GPT-5.4 Mini measured
LiveCodeBench (Artificial Analysis run)Not measured80.8%Only o3 measured
SciCode52.1%Not measuredOnly GPT-5.4 Mini measured
Terminal-Bench Hard (Artificial Analysis run)52.3%37.1%GPT-5.4 Mini
FrontierCode27.0%Not measuredOnly GPT-5.4 Mini measured
GSO-BenchNot measured8.8%Only o3 measured
WeirdML60.3%52.4%GPT-5.4 Mini
ALE-Bench1188.6933.5GPT-5.4 Mini
LMArena Text: coding14381407GPT-5.4 Mini
LMArena Text: software and IT14361415GPT-5.4 Mini
LMArena WebDev: React1386Not measuredOnly GPT-5.4 Mini measured
LMArena WebDev: HTML1419Not measuredOnly GPT-5.4 Mini measured
Neither model has a result on the other 15 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for GPT-5.4 Mini and o3
BenchmarkGPT-5.4 Minio3Leader
AA Intelligence Index24.120.2GPT-5.4 Mini
Epoch Capabilities Index148.7146.7GPT-5.4 Mini
Agentic workLike-for-likePublic boards, shown as published, kept out of the index11
Agentic work benchmarks for GPT-5.4 Mini and o3
BenchmarkGPT-5.4 Minio3Leader
AA Agentic Index17.9Not measuredOnly GPT-5.4 Mini measured
Finance Agent (Vals AI)45.4%Not measuredOnly GPT-5.4 Mini measured
Tax Agent Bench (Vals AI)8.8%Not measuredOnly GPT-5.4 Mini measured
Legal Research Bench (Vals AI)12.5%Not measuredOnly GPT-5.4 Mini measured
Excel Modeling Benchmark (Vals AI)45.4%Not measuredOnly GPT-5.4 Mini measured
τ²-Bench Telecom83.3%80.7%GPT-5.4 Mini
METR time horizonsNot measured65.4%Only o3 measured
GDPvalNot measured30.8%Only o3 measured
DeepResearch Bench36.3%45.2%o3
OSWorldNot measured23.0%Only o3 measured
Neither model has a result on the other 29 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index104
Reasoning benchmarks for GPT-5.4 Mini and o3
BenchmarkGPT-5.4 Minio3Leader
GPQA Diamond83.1%84.1%o3
MMMU Pro (Vals AI)79.3%80.4%o3
GPQA Diamond (Artificial Analysis run)87.5%82.7%GPT-5.4 Mini
Humanity's Last Exam (Artificial Analysis run)28.1%20.1%GPT-5.4 Mini
GPQA Diamond (Epoch AI run)86.9%81.8%GPT-5.4 Mini
ARC-AGI63.7%60.8%GPT-5.4 Mini
ARC-AGI-218.9%6.5%GPT-5.4 Mini
SimpleBenchNot measured53.1%Only o3 measured
Chess puzzles23.0%37.0%o3
Mystery game puzzles11.0%29.0%o3
VPCTNot measured52.0%Only o3 measured
LMArena Text: hard prompts14241402GPT-5.4 Mini
LMArena Text: expert14351402GPT-5.4 Mini
LMArena Text: hard prompts in English14201411GPT-5.4 Mini
LMArena Vision: diagrams12661220GPT-5.4 Mini
LMArena Vision: homework12851234GPT-5.4 Mini
Neither model has a result on the other 5 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index41
Math benchmarks for GPT-5.4 Mini and o3
BenchmarkGPT-5.4 Minio3Leader
AIME95.6%85.3%GPT-5.4 Mini
MATH 500 (Vals AI)Not measured94.6%Only o3 measured
MGSM (Vals AI)Not measured91.8%Only o3 measured
AA Math IndexNot measured88.3Only o3 measured
AIME 2025 (Artificial Analysis run)Not measured88.3%Only o3 measured
OTIS Mock AIME88.9%84.4%GPT-5.4 Mini
FrontierMath, tiers 1 to 351.2%33.3%GPT-5.4 Mini
FrontierMath, tier 49.8%Not measuredOnly GPT-5.4 Mini measured
ProofBench21.0%Not measuredOnly GPT-5.4 Mini measured
MATH level 5Not measured97.8%Only o3 measured
LMArena Text: math14181426o3
LMArena Text: mathematical work14291423GPT-5.4 Mini
Neither model has a result on the other 1 board here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index27
Knowledge benchmarks for GPT-5.4 Mini and o3
BenchmarkGPT-5.4 Minio3Leader
MMLU Pro84.5%85.6%o3
LegalBench (Vals AI)Not measured83.8%Only o3 measured
CaseLaw (Vals AI)51.7%Not measuredOnly GPT-5.4 Mini measured
CorpFin (Vals AI)60.9%59.7%GPT-5.4 Mini
TaxEval (Vals AI)71.2%74.6%o3
MortgageTax (Vals AI)63.5%65.7%o3
MedQA (Vals AI)Not measured96.1%Only o3 measured
MedCode (Vals AI)Not measured47.3%Only o3 measured
MMLU Pro (Artificial Analysis run)Not measured85.3%Only o3 measured
SimpleQA Verified29.4%49.4%o3
GeoBenchNot measured74.0%Only o3 measured
LMArena Text: science14171429o3
LMArena Text: medicine and healthcare13951448o3
LMArena Text: legal and government14141428o3
LMArena Text: business and finance14181393GPT-5.4 Mini
Neither model has a result on the other 2 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
Web design benchmarks for GPT-5.4 Mini and o3
BenchmarkGPT-5.4 Minio3Leader
Design Arena: websitesNot measured1036Only o3 measured
Design Arena: UI componentsNot measured1016Only o3 measured
Design Arena: game devNot measured1034Only o3 measured
Design Arena: data vizNot measured1200Only o3 measured
Design Arena: all code categoriesNot measured1021Only o3 measured
Neither model has a result on the other 4 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index236
General benchmarks for GPT-5.4 Mini and o3
BenchmarkGPT-5.4 Minio3Leader
SAGE (Vals AI)50.8%41.8%GPT-5.4 Mini
MedScribe (Vals AI)Not measured76.7%Only o3 measured
Vals Multimodal Index54.2%Not measuredOnly GPT-5.4 Mini measured
IFBench73.3%71.4%GPT-5.4 Mini
Long context reasoning (AA-LCR)77.0%74.7%GPT-5.4 Mini
DTBench80.0%84.8%o3
LMCA40.8%39.7%GPT-5.4 Mini
Fiction.LiveBenchNot measured88.9%Only o3 measured
Creative writing (Lech Mazur)Not measured83.9%Only o3 measured
CL-benchNot measured17.8%Only o3 measured
LMArena Text14121410GPT-5.4 Mini
LMArena Text: instruction following14051368GPT-5.4 Mini
LMArena Text: creative writing13701359GPT-5.4 Mini
LMArena Vision12451214GPT-5.4 Mini
LMArena Text: English14121417o3
LMArena Text: non-English14051401GPT-5.4 Mini
LMArena Text: Chinese14461437GPT-5.4 Mini
LMArena Text: German14081420o3
LMArena Text: Japanese13751403o3
LMArena Text: Korean13701370GPT-5.4 Mini
LMArena Text: French14411430GPT-5.4 Mini
LMArena Text: Spanish14051395GPT-5.4 Mini
LMArena Text: Russian14171406GPT-5.4 Mini
LMArena Text: Polish14151438o3
LMArena Text: multi-turn14291405GPT-5.4 Mini
LMArena Text: longer queries14081372GPT-5.4 Mini
LMArena Text: writing and language13931372GPT-5.4 Mini
LMArena Text: entertainment and media13731373GPT-5.4 Mini
LMArena Vision: English12441221GPT-5.4 Mini
LMArena Vision: Chinese12861237GPT-5.4 Mini
LMArena Vision: reading text12531218GPT-5.4 Mini
LMArena Vision: humor12351222GPT-5.4 Mini
LMArena Vision: captioningNot measured1210Only o3 measured
LMArena Vision: recognizing things12181234o3
LMArena Vision: creative writing12221201GPT-5.4 Mini
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 GPT-5.4 Mini and o3
BenchmarkGPT-5.4 Minio3Leader
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-5.4 Mini$0.0030Fits in one request
o3$0.0060Fits in one request

GPT-5.4 Mini costs less

Repository review

50K input + 3K output tokens

GPT-5.4 Mini$0.051Fits in one request
o3$0.124Fits in one request

GPT-5.4 Mini costs less

Agent loop

200K input + 10K output tokens

GPT-5.4 Mini$0.195Fits in one request
o3$0.480Exceeds the context window

GPT-5.4 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-5.4 Mini and o3
SpecificationOpenAI GPT-5.4 MiniOpenAI o3
MakerOpenAIOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedMarch 17, 2026April 16, 2025
Context window400K200K
Input $/Mtok$0.75$2.00
Output $/Mtok$4.50$8.00
Coding index28.270.7
Independent measurements behind it12
Cost per solved task$0.70$0.571
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-5.4 Mini better than o3 for coding?

Pick o3 for coding: it scores 70.7 on the Vibe Coding Index against 28.2 for GPT-5.4 Mini. Pick GPT-5.4 Mini when output tokens cost 1.8x less, or when the context window is larger, 400K against 200K tokens.

Which is cheaper, GPT-5.4 Mini or o3?

GPT-5.4 Mini costs $0.75 per million input tokens and $4.50 per million output tokens; o3 costs $2.00 and $8.00. Per solved SWE-bench Verified task, GPT-5.4 Mini costs $0.70 and o3 $0.571.

Which has the bigger context window, GPT-5.4 Mini or o3?

GPT-5.4 Mini, with 400K tokens against 200K.

How many benchmarks is the GPT-5.4 Mini vs o3 comparison based on?

67 benchmarks have a result for both models as of October 21, 2026. GPT-5.4 Mini's coding index rests on 1 independent benchmark and o3's on 2. Where only one model has a result, the page says so instead of naming a winner.

Compare next