Enter opens the highlighted result. Esc closes.

Claude Opus 5 vs GPT-5.4

Claude Opus 5 leads GPT-5.4 on coding, 83.0 to 64.4 on the Vibe Coding Index, and GPT-5.4 costs 1.7x less per output token ($15.00 vs $25.00 per million). Updated October 22, 2026; 95 benchmarks have a result for both.

Replace Claude Opus 5 Replace GPT-5.4
Claude Opus 5Anthropic
Coding
83.0
Overall
81.6
Output $/M
$25.00
93
GPT-5.4OpenAI
Coding
64.4
Overall
69.6
Output $/M
$15.00
1
vs boards won of 95 shared, 1 tied

Claude Opus 5 or GPT-5.4: which to pick

Pick Claude Opus 5 for coding: it scores 83.0 on the Vibe Coding Index against 64.4 for GPT-5.4.

Pick GPT-5.4 for output tokens 1.7x cheaper ($15.00 vs $25.00 per million) and a lower cost per solved task ($1.02 against $1.33).

Model AClaude Opus 5Anthropic83.0/1006 independent benchmarks$1.33 per solved taskModel BGPT-5.4OpenAI64.4/1003 independent benchmarks$1.02 per solved task
Shared results
95
Claude Opus 5 only
36
GPT-5.4 only
15
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
Claude Opus 5 83.0 from 6 benchmarks, GPT-5.4 64.4 from 3 benchmarks.
Widest category
Agentic work, 25.2 points apart on average over 8 shared benchmarks.
Widest single gap
ProofBench: Claude Opus 5 99.0% against GPT-5.4 56.0%, 43.0 points apart on a 0 to 100 scale.
Output price
Claude Opus 5 $25.00 against GPT-5.4 $15.00 per million output tokens, 1.7x apart.
Context window
Claude Opus 5 takes 1M tokens, GPT-5.4 1.05M.

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 5BarsGPT-5.4Ties
Coding150
Intelligence20
Agentic work80
Reasoning141
Math60
Knowledge110
Web design80
General2901 tie
All shared boards9311 tie
CodingLike-for-likeSix of these boards feed the Vibe Coding Index150
Coding benchmarks for Claude Opus 5 and GPT-5.4
BenchmarkClaude Opus 5GPT-5.4Leader
LiveBench coding90.8%Not measuredOnly Claude Opus 5 measured
LMArena WebDev16891464Claude Opus 5
AA Coding Index78.071.1Claude Opus 5
LiveCodeBench (Vals AI)89.0%84.1%Claude Opus 5
SWE-bench Verified (Vals AI)97.0%78.2%Claude Opus 5
Terminal-Bench 4 (Vals AI)53.5%Not measuredOnly Claude Opus 5 measured
Vibe Code Bench (Vals AI)88.4%67.4%Claude Opus 5
Code migration (Vals AI)57.5%35.0%Claude Opus 5
ProgramBench (Vals AI)3.0%0.5%Claude Opus 5
IOI (Vals AI)84.3%Not measuredOnly Claude Opus 5 measured
Terminal-Bench 2.1 (Vals AI)84.6%Not measuredOnly Claude Opus 5 measured
Vibe Code Bench 1-100 (Vals AI)28.5%Not measuredOnly Claude Opus 5 measured
SkillsBench (Vals AI)60.4%51.7%Claude Opus 5
CyberBench (Vals AI)65.4%Not measuredOnly Claude Opus 5 measured
SciCode56.4%Not measuredOnly Claude Opus 5 measured
Terminal-Bench Hard (Artificial Analysis run)Not measured57.6%Only GPT-5.4 measured
Terminal-BenchNot measured81.8%Only GPT-5.4 measured
FrontierCode53.4%Not measuredOnly Claude Opus 5 measured
FrontierSWE52.0%Not measuredOnly Claude Opus 5 measured
GSO-BenchNot measured31.4%Only GPT-5.4 measured
WeirdML91.8%77.7%Claude Opus 5
MirrorCodeNot measured15.6%Only GPT-5.4 measured
ALE-Bench2164.61607.0Claude Opus 5
LMArena Text: coding15331496Claude Opus 5
LMArena Text: software and IT15271491Claude Opus 5
LMArena WebDev: React17111454Claude Opus 5
LMArena WebDev: HTML16801478Claude Opus 5
LMArena WebDev: from an image16621436Claude Opus 5
SciCode13.8%Not measuredOnly Claude Opus 5 measured
Neither model has a result on the other 10 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Claude Opus 5 and GPT-5.4
BenchmarkClaude Opus 5GPT-5.4Leader
AA Intelligence Index50.839.0Claude Opus 5
Epoch Capabilities Index163.9157.3Claude Opus 5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index80
Agentic work benchmarks for Claude Opus 5 and GPT-5.4
BenchmarkClaude Opus 5GPT-5.4Leader
AA Agentic Index56.5Not measuredOnly Claude Opus 5 measured
Design Arena: agents building web apps12661059Claude Opus 5
Design Arena: agents building full-stack apps13061017Claude Opus 5
Design Arena: agents building mobile apps13481087Claude Opus 5
Design Arena: agents building Android apps12571031Claude Opus 5
Design Arena: agents building Godot games12791135Claude Opus 5
Design Arena: agents building games1261Not measuredOnly Claude Opus 5 measured
Design Arena: PowerPoint slides1240Not measuredOnly Claude Opus 5 measured
LiveBench research88.9%Not measuredOnly Claude Opus 5 measured
LiveBench browser84.0%Not measuredOnly Claude Opus 5 measured
LiveBench long agentic62.1%Not measuredOnly Claude Opus 5 measured
SREBench (Vals AI)12.2%Not measuredOnly Claude Opus 5 measured
Finance Agent (Vals AI)58.6%Not measuredOnly Claude Opus 5 measured
Tax Agent Bench (Vals AI)45.5%Not measuredOnly Claude Opus 5 measured
Legal Research Bench (Vals AI)55.3%Not measuredOnly Claude Opus 5 measured
Excel Modeling Benchmark (Vals AI)73.6%Not measuredOnly Claude Opus 5 measured
BioMysteryBench (Vals AI)79.3%Not measuredOnly Claude Opus 5 measured
Terminal-Bench-Science (Vals AI)27.1%Not measuredOnly Claude Opus 5 measured
Vals Science Index47.9%Not measuredOnly Claude Opus 5 measured
Time Horizon Index (Vals AI)18.8%Not measuredOnly Claude Opus 5 measured
CUA-bench (Vals AI)9.0%Not measuredOnly Claude Opus 5 measured
τ²-Bench TelecomNot measured87.1%Only GPT-5.4 measured
APEX-Agents65.8%52.4%Claude Opus 5
METR time horizonsNot measured74.3%Only GPT-5.4 measured
OSWorld 2.031.4%Not measuredOnly Claude Opus 5 measured
BALROG63.4%Not measuredOnly Claude Opus 5 measured
DeepResearch BenchNot measured35.1%Only GPT-5.4 measured
PostTrainBench35.0%19.0%Claude Opus 5
Vending-Bench 2$11,182$6,144Claude Opus 5
LMArena Search1242Not measuredOnly Claude Opus 5 measured
Neither model has a result on the other 11 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index141
Reasoning benchmarks for Claude Opus 5 and GPT-5.4
BenchmarkClaude Opus 5GPT-5.4Leader
GPQA Diamond93.4%91.7%Claude Opus 5
LiveBench reasoning91.2%Not measuredOnly Claude Opus 5 measured
MysteryMechanism (Vals AI)37.4%Not measuredOnly Claude Opus 5 measured
MMMU Pro (Vals AI)89.9%87.5%Claude Opus 5
GPQA Diamond (Artificial Analysis run)93.7%92.0%Claude Opus 5
Humanity's Last Exam (Artificial Analysis run)54.9%43.7%Claude Opus 5
GPQA Diamond (Epoch AI run)93.9%93.3%Claude Opus 5
ARC-AGI97.5%93.7%Claude Opus 5
ARC-AGI-290.4%74.0%Claude Opus 5
SimpleBench80.6%Not measuredOnly Claude Opus 5 measured
Chess puzzles43.0%48.0%GPT-5.4
Mystery game puzzles59.0%37.0%Claude Opus 5
EBR-bench45.7%25.4%Claude Opus 5
LMArena Text: hard prompts15271485Claude Opus 5
LMArena Text: expert15541507Claude Opus 5
LMArena Text: hard prompts in English15231479Claude Opus 5
LMArena Vision: diagrams13481327Claude Opus 5
LMArena Vision: homework13381336Claude Opus 5
Kagi LLM BenchmarkNot measured63.8%Only GPT-5.4 measured
Neither model has a result on the other 3 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index60
Math benchmarks for Claude Opus 5 and GPT-5.4
BenchmarkClaude Opus 5GPT-5.4Leader
AIMENot measured96.7%Only GPT-5.4 measured
OTIS Mock AIME98.9%97.8%Claude Opus 5
FrontierMath, tiers 1 to 385.6%78.6%Claude Opus 5
FrontierMath, tier 473.2%49.0%Claude Opus 5
ProofBench99.0%56.0%Claude Opus 5
LMArena Text: math15331488Claude Opus 5
LMArena Text: mathematical work15441497Claude Opus 5
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index110
Knowledge benchmarks for Claude Opus 5 and GPT-5.4
BenchmarkClaude Opus 5GPT-5.4Leader
MMLU Pro91.6%87.5%Claude Opus 5
LegalBench (Vals AI)87.0%86.0%Claude Opus 5
CaseLaw (Vals AI)Not measured63.8%Only GPT-5.4 measured
CorpFin (Vals AI)73.2%65.3%Claude Opus 5
TaxEval (Vals AI)75.1%74.0%Claude Opus 5
MortgageTax (Vals AI)72.1%68.3%Claude Opus 5
MedQA (Vals AI)Not measured96.1%Only GPT-5.4 measured
MedCode (Vals AI)63.6%41.3%Claude Opus 5
SimpleQA Verified59.9%45.1%Claude Opus 5
LMArena Text: science15311479Claude Opus 5
LMArena Text: medicine and healthcare15251458Claude Opus 5
LMArena Text: legal and government15301486Claude Opus 5
LMArena Text: business and finance15011474Claude Opus 5
Neither model has a result on the other 5 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index80
Web design benchmarks for Claude Opus 5 and GPT-5.4
BenchmarkClaude Opus 5GPT-5.4Leader
Design Arena: websites13091198Claude Opus 5
Design Arena: UI components13461212Claude Opus 5
Design Arena: game dev13371194Claude Opus 5
Design Arena: data viz13291196Claude Opus 5
Design Arena: 3D13341065Claude Opus 5
Design Arena: all code categories13231179Claude Opus 5
Design Arena: SVG13111141Claude Opus 5
Design Arena: ASCII art13521188Claude Opus 5
LiveBench design83.0%Not measuredOnly Claude Opus 5 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index290
General benchmarks for Claude Opus 5 and GPT-5.4
BenchmarkClaude Opus 5GPT-5.4Leader
LiveBench data analysis74.6%Not measuredOnly Claude Opus 5 measured
Public Benefits Bench (Vals AI)76.9%Not measuredOnly Claude Opus 5 measured
SAGE (Vals AI)49.4%43.3%Claude Opus 5
MedScribe (Vals AI)91.0%77.5%Claude Opus 5
Vals Multimodal Index73.9%Not measuredOnly Claude Opus 5 measured
IFBenchNot measured73.9%Only GPT-5.4 measured
Long context reasoning (AA-LCR)82.0%82.0%Tie
DTBench97.9%94.4%Claude Opus 5
LMCA64.5%52.0%Claude Opus 5
CL-benchNot measured27.9%Only GPT-5.4 measured
Furniture assembly60.8%37.5%Claude Opus 5
CL-bench LifeNot measured21.7%Only GPT-5.4 measured
LMArena Text15091469Claude Opus 5
LMArena Text: instruction following15181469Claude Opus 5
LMArena Text: creative writing14931439Claude Opus 5
LMArena Vision13201303Claude Opus 5
LMArena Text: English15081467Claude Opus 5
LMArena Text: non-English15021465Claude Opus 5
LMArena Text: Chinese15731520Claude Opus 5
LMArena Text: German15271472Claude Opus 5
LMArena Text: Japanese15201485Claude Opus 5
LMArena Text: Korean15171449Claude Opus 5
LMArena Text: French15191493Claude Opus 5
LMArena Text: Spanish15231452Claude Opus 5
LMArena Text: Russian15071480Claude Opus 5
LMArena Text: Polish15221472Claude Opus 5
LMArena Text: multi-turn15001482Claude Opus 5
LMArena Text: longer queries15171473Claude Opus 5
LMArena Text: writing and language14991458Claude Opus 5
LMArena Text: entertainment and media14811438Claude Opus 5
LMArena Vision: English13151301Claude Opus 5
LMArena Vision: Chinese14001354Claude Opus 5
LMArena Vision: reading text13291312Claude Opus 5
LMArena Vision: humor12931284Claude Opus 5
LMArena Vision: recognizing thingsNot measured1251Only GPT-5.4 measured
LMArena Vision: creative writing13131283Claude Opus 5
LMArena Document15161471Claude Opus 5
Neither model has a result on the other 9 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Claude Opus 5 and GPT-5.4
BenchmarkClaude Opus 5GPT-5.4Leader
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 5$0.018Fits in one request
GPT-5.4$0.010Fits in one request

GPT-5.4 costs less

Repository review

50K input + 3K output tokens

Claude Opus 5$0.325Fits in one request
GPT-5.4$0.170Fits in one request

GPT-5.4 costs less

Agent loop

200K input + 10K output tokens

Claude Opus 5$1.25Fits in one request
GPT-5.4$0.650Fits in one request

GPT-5.4 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 5 and GPT-5.4
SpecificationAnthropic Claude Opus 5OpenAI GPT-5.4
MakerAnthropicOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedJuly 24, 2026March 5, 2026
Context window1M1.05M
Input $/Mtok$5.00$2.50
Output $/Mtok$25.00$15.00
Coding index83.064.4
Independent measurements behind it63
Cost per solved task$1.33$1.02
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Opus 5 better than GPT-5.4 for coding?

Pick Claude Opus 5 for coding: it scores 83.0 on the Vibe Coding Index against 64.4 for GPT-5.4. Pick GPT-5.4 for output tokens 1.7x cheaper ($15.00 vs $25.00 per million) and a lower cost per solved task ($1.02 against $1.33).

Which is cheaper, Claude Opus 5 or GPT-5.4?

Claude Opus 5 costs $5.00 per million input tokens and $25.00 per million output tokens; GPT-5.4 costs $2.50 and $15.00. Per solved SWE-bench Verified task, Claude Opus 5 costs $1.33 and GPT-5.4 $1.02.

Which has the bigger context window, Claude Opus 5 or GPT-5.4?

GPT-5.4, with 1.05M tokens against 1M.

How many benchmarks is the Claude Opus 5 vs GPT-5.4 comparison based on?

95 benchmarks have a result for both models as of October 22, 2026. Claude Opus 5's coding index rests on 6 independent benchmarks and GPT-5.4's on 3. 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/claude-opus-5-vs-gpt-5-4" title="Claude Opus 5 vs GPT-5.4, 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/claude-opus-5-vs-gpt-5-4">LLMBenchmark.ai, Claude Opus 5 vs GPT-5.4</a></p>