Enter opens the highlighted result. Esc closes.

Claude Opus 4.7 vs GPT-5.4

Claude Opus 4.7 leads GPT-5.4 on coding, 67.5 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; 90 benchmarks have a result for both.

Replace Claude Opus 4.7 Replace GPT-5.4
Claude Opus 4.7Anthropic
Coding
67.5
Overall
71.6
Output $/M
$25.00
66
GPT-5.4OpenAI
Coding
64.4
Overall
69.6
Output $/M
$15.00
24
vs boards won of 90 shared

Claude Opus 4.7 or GPT-5.4: which to pick

Pick Claude Opus 4.7 for coding: it scores 67.5 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 $2.95).

Model AClaude Opus 4.7Anthropic67.5/1004 independent benchmarks$2.95 per solved taskModel BGPT-5.4OpenAI64.4/1003 independent benchmarks$1.02 per solved task
Shared results
90
Claude Opus 4.7 only
13
GPT-5.4 only
20
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
Claude Opus 4.7 67.5 from 4 benchmarks, GPT-5.4 64.4 from 3 benchmarks.
Widest category
Agentic work, 11.0 points apart on average over 4 shared benchmarks.
Widest single gap
Vending-Bench 2: Claude Opus 4.7 $10,937 against GPT-5.4 $6,144, 30.0 points apart on a 0 to 100 scale.
Output price
Claude Opus 4.7 $25.00 against GPT-5.4 $15.00 per million output tokens, 1.7x apart.
Context window
Claude Opus 4.7 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 4.7BarsGPT-5.4Ties
Coding134
Intelligence11
Agentic work31
Reasoning79
Math34
Knowledge111
General284
All shared boards6624
CodingLike-for-likeSix of these boards feed the Vibe Coding Index134
Coding benchmarks for Claude Opus 4.7 and GPT-5.4
BenchmarkClaude Opus 4.7GPT-5.4Leader
LMArena WebDev15581464Claude Opus 4.7
AA Coding Index73.671.1Claude Opus 4.7
LiveCodeBench (Vals AI)85.1%84.1%Claude Opus 4.7
SWE-bench Verified (Vals AI)82.0%78.2%Claude Opus 4.7
Vibe Code Bench (Vals AI)71.0%67.4%Claude Opus 4.7
Code migration (Vals AI)43.9%35.0%Claude Opus 4.7
ProgramBench (Vals AI)0.0%0.5%GPT-5.4
Terminal-Bench 2.1 (Vals AI)68.5%Not measuredOnly Claude Opus 4.7 measured
SkillsBench (Vals AI)Not measured51.7%Only GPT-5.4 measured
Terminal-Bench Hard (Artificial Analysis run)54.5%57.6%GPT-5.4
Terminal-Bench80.2%81.8%GPT-5.4
FrontierCode38.5%Not measuredOnly Claude Opus 4.7 measured
GSO-Bench44.1%31.4%Claude Opus 4.7
WeirdML76.4%77.7%GPT-5.4
MirrorCode31.1%15.6%Claude Opus 4.7
ALE-BenchNot measured1607.0Only GPT-5.4 measured
LMArena Text: coding15191496Claude Opus 4.7
LMArena Text: software and IT15161491Claude Opus 4.7
LMArena WebDev: React15601454Claude Opus 4.7
LMArena WebDev: HTML15541478Claude Opus 4.7
LMArena WebDev: from an image15771436Claude Opus 4.7
Neither model has a result on the other 18 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index11
Intelligence benchmarks for Claude Opus 4.7 and GPT-5.4
BenchmarkClaude Opus 4.7GPT-5.4Leader
AA Intelligence Index40.739.0Claude Opus 4.7
Epoch Capabilities Index156.8157.3GPT-5.4
Agentic workLike-for-likePublic boards, shown as published, kept out of the index31
Agentic work benchmarks for Claude Opus 4.7 and GPT-5.4
BenchmarkClaude Opus 4.7GPT-5.4Leader
AA Agentic Index38.6Not measuredOnly Claude Opus 4.7 measured
Design Arena: agents building web appsNot measured1059Only GPT-5.4 measured
Design Arena: agents building full-stack appsNot measured1017Only GPT-5.4 measured
Design Arena: agents building mobile appsNot measured1087Only GPT-5.4 measured
Design Arena: agents building Android appsNot measured1031Only GPT-5.4 measured
Design Arena: agents building Godot gamesNot measured1135Only GPT-5.4 measured
Finance Agent (Vals AI)51.5%Not measuredOnly Claude Opus 4.7 measured
Tax Agent Bench (Vals AI)23.7%Not measuredOnly Claude Opus 4.7 measured
Legal Research Bench (Vals AI)38.5%Not measuredOnly Claude Opus 4.7 measured
Excel Modeling Benchmark (Vals AI)63.7%Not measuredOnly Claude Opus 4.7 measured
τ²-Bench Telecom88.6%87.1%Claude Opus 4.7
APEX-Agents49.2%52.4%GPT-5.4
METR time horizonsNot measured74.3%Only GPT-5.4 measured
OSWorld 2.018.2%Not measuredOnly Claude Opus 4.7 measured
DeepResearch BenchNot measured35.1%Only GPT-5.4 measured
PostTrainBench28.6%19.0%Claude Opus 4.7
Vending-Bench 2$10,937$6,144Claude Opus 4.7
LMArena Search1230Not measuredOnly Claude Opus 4.7 measured
Neither model has a result on the other 23 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index79
Reasoning benchmarks for Claude Opus 4.7 and GPT-5.4
BenchmarkClaude Opus 4.7GPT-5.4Leader
GPQA Diamond90.2%91.7%GPT-5.4
MMMU Pro (Vals AI)85.5%87.5%GPT-5.4
GPQA Diamond (Artificial Analysis run)91.4%92.0%GPT-5.4
Humanity's Last Exam (Artificial Analysis run)42.3%43.7%GPT-5.4
GPQA Diamond (Epoch AI run)90.2%93.3%GPT-5.4
ARC-AGI93.5%93.7%GPT-5.4
ARC-AGI-275.8%74.0%Claude Opus 4.7
SimpleBench61.7%Not measuredOnly Claude Opus 4.7 measured
Chess puzzles41.0%48.0%GPT-5.4
Mystery game puzzles28.0%37.0%GPT-5.4
EBR-bench19.0%25.4%GPT-5.4
LMArena Text: hard prompts15061485Claude Opus 4.7
LMArena Text: expert15211507Claude Opus 4.7
LMArena Text: hard prompts in English15081479Claude Opus 4.7
LMArena Vision: diagrams13361327Claude Opus 4.7
LMArena Vision: homework13371336Claude Opus 4.7
Kagi LLM Benchmark80.7%63.8%Claude Opus 4.7
Neither model has a result on the other 5 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index34
Math benchmarks for Claude Opus 4.7 and GPT-5.4
BenchmarkClaude Opus 4.7GPT-5.4Leader
AIME96.3%96.7%GPT-5.4
OTIS Mock AIME97.8%97.8%Claude Opus 4.7
FrontierMath, tiers 1 to 370.2%78.6%GPT-5.4
FrontierMath, tier 431.7%49.0%GPT-5.4
ProofBench54.0%56.0%GPT-5.4
LMArena Text: math14981488Claude Opus 4.7
LMArena Text: mathematical work15091497Claude Opus 4.7
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index111
Knowledge benchmarks for Claude Opus 4.7 and GPT-5.4
BenchmarkClaude Opus 4.7GPT-5.4Leader
MMLU Pro89.9%87.5%Claude Opus 4.7
LegalBench (Vals AI)85.3%86.0%GPT-5.4
CaseLaw (Vals AI)68.4%63.8%Claude Opus 4.7
CorpFin (Vals AI)66.1%65.3%Claude Opus 4.7
TaxEval (Vals AI)75.3%74.0%Claude Opus 4.7
MortgageTax (Vals AI)70.3%68.3%Claude Opus 4.7
MedQA (Vals AI)Not measured96.1%Only GPT-5.4 measured
MedCode (Vals AI)54.9%41.3%Claude Opus 4.7
SimpleQA Verified51.7%45.1%Claude Opus 4.7
LMArena Text: science15081479Claude Opus 4.7
LMArena Text: medicine and healthcare14951458Claude Opus 4.7
LMArena Text: legal and government15041486Claude Opus 4.7
LMArena Text: business and finance14901474Claude Opus 4.7
FACTS Benchmark Suite45.5%Not measuredOnly Claude Opus 4.7 measured
Neither model has a result on the other 4 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
Web design benchmarks for Claude Opus 4.7 and GPT-5.4
BenchmarkClaude Opus 4.7GPT-5.4Leader
Design Arena: websitesNot measured1198Only GPT-5.4 measured
Design Arena: UI componentsNot measured1212Only GPT-5.4 measured
Design Arena: game devNot measured1194Only GPT-5.4 measured
Design Arena: data vizNot measured1196Only GPT-5.4 measured
Design Arena: 3DNot measured1065Only GPT-5.4 measured
Design Arena: all code categoriesNot measured1179Only GPT-5.4 measured
Design Arena: SVGNot measured1141Only GPT-5.4 measured
Design Arena: ASCII artNot measured1188Only GPT-5.4 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index284
General benchmarks for Claude Opus 4.7 and GPT-5.4
BenchmarkClaude Opus 4.7GPT-5.4Leader
SAGE (Vals AI)56.1%43.3%Claude Opus 4.7
MedScribe (Vals AI)83.0%77.5%Claude Opus 4.7
Vals Multimodal Index67.4%Not measuredOnly Claude Opus 4.7 measured
IFBench58.6%73.9%GPT-5.4
Long context reasoning (AA-LCR)78.7%82.0%GPT-5.4
DTBench94.7%94.4%Claude Opus 4.7
LMCA52.2%52.0%Claude Opus 4.7
CL-benchNot measured27.9%Only GPT-5.4 measured
Furniture assembly33.3%37.5%GPT-5.4
ExploitBench26.5%Not measuredOnly Claude Opus 4.7 measured
CL-bench LifeNot measured21.7%Only GPT-5.4 measured
LMArena Text14901469Claude Opus 4.7
LMArena Text: instruction following14981469Claude Opus 4.7
LMArena Text: creative writing14861439Claude Opus 4.7
LMArena Vision13171303Claude Opus 4.7
LMArena Text: English14961467Claude Opus 4.7
LMArena Text: non-English14801465Claude Opus 4.7
LMArena Text: Chinese15311520Claude Opus 4.7
LMArena Text: German14951472Claude Opus 4.7
LMArena Text: Japanese14741485GPT-5.4
LMArena Text: Korean14641449Claude Opus 4.7
LMArena Text: French15031493Claude Opus 4.7
LMArena Text: Spanish14941452Claude Opus 4.7
LMArena Text: Russian14941480Claude Opus 4.7
LMArena Text: Polish14891472Claude Opus 4.7
LMArena Text: multi-turn15051482Claude Opus 4.7
LMArena Text: longer queries15051473Claude Opus 4.7
LMArena Text: writing and language14921458Claude Opus 4.7
LMArena Text: entertainment and media14741438Claude Opus 4.7
LMArena Vision: English13221301Claude Opus 4.7
LMArena Vision: Chinese13711354Claude Opus 4.7
LMArena Vision: reading text13271312Claude Opus 4.7
LMArena Vision: humor13091284Claude Opus 4.7
LMArena Vision: recognizing things12781251Claude Opus 4.7
LMArena Vision: creative writing13261283Claude Opus 4.7
LMArena Document14951471Claude Opus 4.7
Neither model has a result on the other 10 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Claude Opus 4.7 and GPT-5.4
BenchmarkClaude Opus 4.7GPT-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 4.7$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 4.7$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 4.7$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 4.7 and GPT-5.4
SpecificationAnthropic Claude Opus 4.7OpenAI GPT-5.4
MakerAnthropicOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedApril 16, 2026March 5, 2026
Context window1M1.05M
Input $/Mtok$5.00$2.50
Output $/Mtok$25.00$15.00
Coding index67.564.4
Independent measurements behind it43
Cost per solved task$2.95$1.02
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Opus 4.7 better than GPT-5.4 for coding?

Pick Claude Opus 4.7 for coding: it scores 67.5 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 $2.95).

Which is cheaper, Claude Opus 4.7 or GPT-5.4?

Claude Opus 4.7 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 4.7 costs $2.95 and GPT-5.4 $1.02.

Which has the bigger context window, Claude Opus 4.7 or GPT-5.4?

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

How many benchmarks is the Claude Opus 4.7 vs GPT-5.4 comparison based on?

90 benchmarks have a result for both models as of October 22, 2026. Claude Opus 4.7's coding index rests on 4 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-4-7-vs-gpt-5-4" title="Claude Opus 4.7 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-4-7-vs-gpt-5-4">LLMBenchmark.ai, Claude Opus 4.7 vs GPT-5.4</a></p>