Enter opens the highlighted result. Esc closes.

Claude Opus 4.5 vs GPT-5.4 Mini

Updated October 21, 2026. 65 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Claude Opus 4.5 Replace GPT-5.4 Mini
Claude Opus 4.5Anthropic
Coding
66.8
Overall
29.1
Output $/M
$25.00
55
GPT-5.4 MiniOpenAI
Coding
28.2
Overall
24.1
Output $/M
$4.50
10
vs boards won of 65 shared

Decision reading

Pick Claude Opus 4.5 for coding: it scores 66.8 on the Vibe Coding Index against 28.2 for GPT-5.4 Mini.

Pick GPT-5.4 Mini when output tokens cost 5.6x less, or when a solved task costs $0.70 against $1.37.

Model AClaude Opus 4.5Anthropic66.8/1002 independent benchmarks$1.37 per solved taskModel BGPT-5.4 MiniOpenAI28.2/1001 independent benchmark$0.70 per solved task
Shared results
65
Claude Opus 4.5 only
40
GPT-5.4 Mini only
23
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
Claude Opus 4.5 66.8 from 2 benchmarks, GPT-5.4 Mini 28.2 from 1 benchmark.
Widest category
Agentic work, 12.3 points apart on average over 2 shared benchmarks.
Widest single gap
Vibe Code Bench (Vals AI): Claude Opus 4.5 20.6% against GPT-5.4 Mini 48.0%, 27.3 points apart on a 0 to 100 scale.
Output price
Claude Opus 4.5 $25.00 against GPT-5.4 Mini $4.50 per million output tokens, 5.6x apart.
Context window
Claude Opus 4.5 takes 200K tokens, GPT-5.4 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
CategoryClaude Opus 4.5BarsGPT-5.4 MiniTies
Coding82
Intelligence20
Agentic work20
Reasoning93
Math34
Knowledge100
General211
All shared boards5510
CodingLike-for-likeFour of these boards feed the Vibe Coding Index82
Coding benchmarks for Claude Opus 4.5 and GPT-5.4 Mini
BenchmarkClaude Opus 4.5GPT-5.4 MiniLeader
SWE-bench Verified79.2%Not measuredOnly Claude Opus 4.5 measured
SWE-bench (full test set)52.6%Not measuredOnly Claude Opus 4.5 measured
SWE-bench Multilingual70.7%Not measuredOnly Claude Opus 4.5 measured
LMArena WebDev14941397Claude Opus 4.5
AA Coding IndexNot measured56.1Only GPT-5.4 Mini measured
LiveCodeBench (Vals AI)83.7%81.5%Claude Opus 4.5
SWE-bench Verified (Vals AI)76.4%73.0%Claude Opus 4.5
Terminal-Bench 4 (Vals AI)Not measured2.5%Only GPT-5.4 Mini measured
Vibe Code Bench (Vals AI)20.6%48.0%GPT-5.4 Mini
Code migration (Vals AI)Not measured12.9%Only GPT-5.4 Mini measured
ProgramBench (Vals AI)Not measured0.0%Only GPT-5.4 Mini measured
Terminal-Bench 2.1 (Vals AI)Not measured54.7%Only GPT-5.4 Mini measured
LiveCodeBench (Artificial Analysis run)87.1%Not measuredOnly Claude Opus 4.5 measured
SciCodeNot measured52.1%Only GPT-5.4 Mini measured
Terminal-Bench Hard (Artificial Analysis run)47.0%52.3%GPT-5.4 Mini
Terminal-Bench63.1%Not measuredOnly Claude Opus 4.5 measured
FrontierCodeNot measured27.0%Only GPT-5.4 Mini measured
GSO-Bench26.5%Not measuredOnly Claude Opus 4.5 measured
WeirdML63.7%60.3%Claude Opus 4.5
Cybench82.0%Not measuredOnly Claude Opus 4.5 measured
ALE-BenchNot measured1188.6Only GPT-5.4 Mini measured
LMArena Text: coding15031438Claude Opus 4.5
LMArena Text: software and IT14831436Claude Opus 4.5
LMArena WebDev: React14781386Claude Opus 4.5
LMArena WebDev: HTML15101419Claude Opus 4.5
Neither model has a result on the other 13 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Claude Opus 4.5 and GPT-5.4 Mini
BenchmarkClaude Opus 4.5GPT-5.4 MiniLeader
AA Intelligence Index29.124.1Claude Opus 4.5
Epoch Capabilities Index150.1148.7Claude Opus 4.5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index20
Agentic work benchmarks for Claude Opus 4.5 and GPT-5.4 Mini
BenchmarkClaude Opus 4.5GPT-5.4 MiniLeader
AA Agentic IndexNot measured17.9Only GPT-5.4 Mini measured
Design Arena: agents building web apps1159Not measuredOnly Claude Opus 4.5 measured
Design Arena: agents building full-stack apps1156Not measuredOnly Claude Opus 4.5 measured
Design Arena: agents building mobile apps1189Not measuredOnly Claude Opus 4.5 measured
Design Arena: agents building Android apps1181Not measuredOnly Claude Opus 4.5 measured
Finance Agent (Vals AI)Not measured45.4%Only GPT-5.4 Mini measured
Tax Agent Bench (Vals AI)Not measured8.8%Only GPT-5.4 Mini measured
Legal Research Bench (Vals AI)Not measured12.5%Only GPT-5.4 Mini measured
Excel Modeling Benchmark (Vals AI)Not measured45.4%Only GPT-5.4 Mini measured
τ²-Bench Telecom89.5%83.3%Claude Opus 4.5
METR time horizons75.0%Not measuredOnly Claude Opus 4.5 measured
Remote Labor Index3.8%Not measuredOnly Claude Opus 4.5 measured
GDPval45.5%Not measuredOnly Claude Opus 4.5 measured
BALROG43.5%Not measuredOnly Claude Opus 4.5 measured
DeepResearch Bench54.8%36.3%Claude Opus 4.5
OSWorld66.3%Not measuredOnly Claude Opus 4.5 measured
Vending-Bench 2$4,967Not measuredOnly Claude Opus 4.5 measured
Neither model has a result on the other 22 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index93
Reasoning benchmarks for Claude Opus 4.5 and GPT-5.4 Mini
BenchmarkClaude Opus 4.5GPT-5.4 MiniLeader
GPQA Diamond85.9%83.1%Claude Opus 4.5
MMMU Pro (Vals AI)83.0%79.3%Claude Opus 4.5
GPQA Diamond (Artificial Analysis run)86.6%87.5%GPT-5.4 Mini
Humanity's Last Exam (Artificial Analysis run)30.1%28.1%Claude Opus 4.5
GPQA Diamond (Epoch AI run)86.0%86.9%GPT-5.4 Mini
ARC-AGI80.0%63.7%Claude Opus 4.5
ARC-AGI-237.6%18.9%Claude Opus 4.5
SimpleBench62.0%Not measuredOnly Claude Opus 4.5 measured
Chess puzzles14.0%23.0%GPT-5.4 Mini
Mystery game puzzles22.0%11.0%Claude Opus 4.5
EBR-bench14.3%Not measuredOnly Claude Opus 4.5 measured
VPCT40.0%Not measuredOnly Claude Opus 4.5 measured
LMArena Text: hard prompts14761424Claude Opus 4.5
LMArena Text: expert14871435Claude Opus 4.5
LMArena Text: hard prompts in English14821420Claude Opus 4.5
LMArena Vision: diagramsNot measured1266Only GPT-5.4 Mini measured
LMArena Vision: homeworkNot measured1285Only GPT-5.4 Mini measured
Neither model has a result on the other 4 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index34
Math benchmarks for Claude Opus 4.5 and GPT-5.4 Mini
BenchmarkClaude Opus 4.5GPT-5.4 MiniLeader
AIME95.4%95.6%GPT-5.4 Mini
MGSM (Vals AI)95.2%Not measuredOnly Claude Opus 4.5 measured
AA Math Index91.3Not measuredOnly Claude Opus 4.5 measured
AIME 2025 (Artificial Analysis run)91.3%Not measuredOnly Claude Opus 4.5 measured
OTIS Mock AIME86.1%88.9%GPT-5.4 Mini
FrontierMath, tiers 1 to 334.4%51.2%GPT-5.4 Mini
FrontierMath, tier 44.9%9.8%GPT-5.4 Mini
ProofBench36.0%21.0%Claude Opus 4.5
LMArena Text: math14631418Claude Opus 4.5
LMArena Text: mathematical work14681429Claude Opus 4.5
Neither model has a result on the other 3 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index100
Knowledge benchmarks for Claude Opus 4.5 and GPT-5.4 Mini
BenchmarkClaude Opus 4.5GPT-5.4 MiniLeader
MMLU Pro87.3%84.5%Claude Opus 4.5
LegalBench (Vals AI)84.6%Not measuredOnly Claude Opus 4.5 measured
CaseLaw (Vals AI)62.6%51.7%Claude Opus 4.5
CorpFin (Vals AI)65.1%60.9%Claude Opus 4.5
TaxEval (Vals AI)74.9%71.2%Claude Opus 4.5
MortgageTax (Vals AI)68.7%63.5%Claude Opus 4.5
MedQA (Vals AI)95.9%Not measuredOnly Claude Opus 4.5 measured
MedCode (Vals AI)49.2%Not measuredOnly Claude Opus 4.5 measured
MMLU Pro (Artificial Analysis run)89.5%Not measuredOnly Claude Opus 4.5 measured
SimpleQA Verified45.7%29.4%Claude Opus 4.5
GeoBench75.0%Not measuredOnly Claude Opus 4.5 measured
LMArena Text: science14541417Claude Opus 4.5
LMArena Text: medicine and healthcare14441395Claude Opus 4.5
LMArena Text: legal and government14591414Claude Opus 4.5
LMArena Text: business and finance14481418Claude Opus 4.5
Neither model has a result on the other 2 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
Web design benchmarks for Claude Opus 4.5 and GPT-5.4 Mini
BenchmarkClaude Opus 4.5GPT-5.4 MiniLeader
Design Arena: websites1247Not measuredOnly Claude Opus 4.5 measured
Design Arena: UI components1238Not measuredOnly Claude Opus 4.5 measured
Design Arena: game dev1229Not measuredOnly Claude Opus 4.5 measured
Design Arena: data viz1243Not measuredOnly Claude Opus 4.5 measured
Design Arena: 3D1214Not measuredOnly Claude Opus 4.5 measured
Design Arena: all code categories1242Not measuredOnly Claude Opus 4.5 measured
Design Arena: SVG1180Not measuredOnly Claude Opus 4.5 measured
Design Arena: ASCII art1190Not measuredOnly Claude Opus 4.5 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index211
General benchmarks for Claude Opus 4.5 and GPT-5.4 Mini
BenchmarkClaude Opus 4.5GPT-5.4 MiniLeader
SAGE (Vals AI)52.1%50.8%Claude Opus 4.5
MedScribe (Vals AI)85.3%Not measuredOnly Claude Opus 4.5 measured
Vals Multimodal IndexNot measured54.2%Only GPT-5.4 Mini measured
IFBench58.0%73.3%GPT-5.4 Mini
Long context reasoning (AA-LCR)77.3%77.0%Claude Opus 4.5
DTBench89.9%80.0%Claude Opus 4.5
LMCA44.5%40.8%Claude Opus 4.5
CL-bench21.1%Not measuredOnly Claude Opus 4.5 measured
Furniture assembly28.3%Not measuredOnly Claude Opus 4.5 measured
LMArena Text14511412Claude Opus 4.5
LMArena Text: instruction following14781405Claude Opus 4.5
LMArena Text: creative writing14451370Claude Opus 4.5
LMArena VisionNot measured1245Only GPT-5.4 Mini measured
LMArena Text: English14611412Claude Opus 4.5
LMArena Text: non-English14381405Claude Opus 4.5
LMArena Text: Chinese14701446Claude Opus 4.5
LMArena Text: German14491408Claude Opus 4.5
LMArena Text: Japanese14171375Claude Opus 4.5
LMArena Text: Korean14241370Claude Opus 4.5
LMArena Text: French14711441Claude Opus 4.5
LMArena Text: Spanish14571405Claude Opus 4.5
LMArena Text: Russian14471417Claude Opus 4.5
LMArena Text: Polish14391415Claude Opus 4.5
LMArena Text: multi-turn14661429Claude Opus 4.5
LMArena Text: longer queries14791408Claude Opus 4.5
LMArena Text: writing and language14521393Claude Opus 4.5
LMArena Text: entertainment and media14341373Claude Opus 4.5
LMArena Vision: EnglishNot measured1244Only GPT-5.4 Mini measured
LMArena Vision: ChineseNot measured1286Only GPT-5.4 Mini measured
LMArena Vision: reading textNot measured1253Only GPT-5.4 Mini measured
LMArena Vision: humorNot measured1235Only GPT-5.4 Mini measured
LMArena Vision: recognizing thingsNot measured1218Only GPT-5.4 Mini measured
LMArena Vision: creative writingNot measured1222Only GPT-5.4 Mini measured
LMArena Document1462Not measuredOnly Claude Opus 4.5 measured
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 Claude Opus 4.5 and GPT-5.4 Mini
BenchmarkClaude Opus 4.5GPT-5.4 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

Claude Opus 4.5$0.018Fits in one request
GPT-5.4 Mini$0.0030Fits in one request

GPT-5.4 Mini costs less

Repository review

50K input + 3K output tokens

Claude Opus 4.5$0.325Fits in one request
GPT-5.4 Mini$0.051Fits in one request

GPT-5.4 Mini costs less

Agent loop

200K input + 10K output tokens

Claude Opus 4.5$1.25Exceeds the context window
GPT-5.4 Mini$0.195Fits in one request

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 Claude Opus 4.5 and GPT-5.4 Mini
SpecificationAnthropic Claude Opus 4.5OpenAI GPT-5.4 Mini
MakerAnthropicOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedNovember 24, 2025March 17, 2026
Context window200K400K
Input $/Mtok$5.00$0.75
Output $/Mtok$25.00$4.50
Coding index66.828.2
Independent measurements behind it21
Cost per solved task$1.37$0.70
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Opus 4.5 better than GPT-5.4 Mini for coding?

Pick Claude Opus 4.5 for coding: it scores 66.8 on the Vibe Coding Index against 28.2 for GPT-5.4 Mini. Pick GPT-5.4 Mini when output tokens cost 5.6x less, or when a solved task costs $0.70 against $1.37.

Which is cheaper, Claude Opus 4.5 or GPT-5.4 Mini?

Claude Opus 4.5 costs $5.00 per million input tokens and $25.00 per million output tokens; GPT-5.4 Mini costs $0.75 and $4.50. Per solved SWE-bench Verified task, Claude Opus 4.5 costs $1.37 and GPT-5.4 Mini $0.70.

Which has the bigger context window, Claude Opus 4.5 or GPT-5.4 Mini?

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

How many benchmarks is the Claude Opus 4.5 vs GPT-5.4 Mini comparison based on?

65 benchmarks have a result for both models as of October 21, 2026. Claude Opus 4.5's coding index rests on 2 independent benchmarks and GPT-5.4 Mini's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next