Enter opens the highlighted result. Esc closes.

Claude Opus 4.5 vs GPT-5

Claude Opus 4.5 leads GPT-5 on coding, 44.0 to 38.8 on the Vibe Coding Index, and GPT-5 costs 2.5x less per output token ($10.00 vs $25.00 per million). Updated October 22, 2026; 94 benchmarks have a result for both.

Replace Claude Opus 4.5 Replace GPT-5
Claude Opus 4.5Anthropic
Coding
44.0
Overall
55.7
Output $/M
$25.00
73
GPT-5OpenAI
Coding
38.8
Overall
51.5
Output $/M
$10.00
21
vs boards won of 94 shared

Claude Opus 4.5 or GPT-5: which to pick

Pick Claude Opus 4.5 for coding: it scores 44.0 on the Vibe Coding Index against 38.8 for GPT-5.

Pick GPT-5 for output tokens 2.5x cheaper ($10.00 vs $25.00 per million) and a lower cost per solved task ($0.39 against $1.37).

Model AClaude Opus 4.5Anthropic44.0/1003 independent benchmarks$1.37 per solved taskModel BGPT-5OpenAI38.8/1003 independent benchmarks$0.39 per solved task
Shared results
94
Claude Opus 4.5 only
14
GPT-5 only
19
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 4.5 44.0 from 3 benchmarks, GPT-5 38.8 from 3 benchmarks.
Widest category
Math, 9.2 points apart on average over 10 shared benchmarks.
Widest single gap
ARC-AGI-2: Claude Opus 4.5 37.6% against GPT-5 9.9%, 27.8 points apart on a 0 to 100 scale.
Output price
Claude Opus 4.5 $25.00 against GPT-5 $10.00 per million output tokens, 2.5x apart.
Context window
Claude Opus 4.5 takes 200K tokens, GPT-5 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-5Ties
Coding121
Intelligence20
Agentic work60
Reasoning124
Math55
Knowledge97
Web design71
General203
All shared boards7321
CodingLike-for-likeSix of these boards feed the Vibe Coding Index121
Coding benchmarks for Claude Opus 4.5 and GPT-5
BenchmarkClaude Opus 4.5GPT-5Leader
Aider polyglotNot measured88.0%Only GPT-5 measured
SWE-bench Verified79.2%74.4%Claude Opus 4.5
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 WebDev14941418Claude Opus 4.5
AA Coding IndexNot measured37.8Only GPT-5 measured
LiveCodeBench (Vals AI)83.7%85.9%GPT-5
SWE-bench Verified (Vals AI)76.4%69.0%Claude Opus 4.5
Vibe Code Bench (Vals AI)20.6%20.1%Claude Opus 4.5
LiveCodeBench (Artificial Analysis run)87.1%84.6%Claude Opus 4.5
Terminal-Bench Hard (Artificial Analysis run)47.0%37.9%Claude Opus 4.5
Terminal-Bench63.1%49.6%Claude Opus 4.5
GSO-Bench26.5%6.9%Claude Opus 4.5
WeirdML63.7%60.7%Claude Opus 4.5
Cybench82.0%Not measuredOnly Claude Opus 4.5 measured
ALE-BenchNot measured807.6Only GPT-5 measured
LMArena Text: coding15031436Claude Opus 4.5
LMArena Text: software and IT14831420Claude Opus 4.5
LMArena WebDev: React1478Not measuredOnly Claude Opus 4.5 measured
LMArena WebDev: HTML15101427Claude Opus 4.5
SciCodeNot measured0.0%Only GPT-5 measured
Neither model has a result on the other 18 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Claude Opus 4.5 and GPT-5
BenchmarkClaude Opus 4.5GPT-5Leader
AA Intelligence Index29.123.0Claude Opus 4.5
Epoch Capabilities Index150.1150.0Claude Opus 4.5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index60
Agentic work benchmarks for Claude Opus 4.5 and GPT-5
BenchmarkClaude Opus 4.5GPT-5Leader
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 apps1176Not measuredOnly Claude Opus 4.5 measured
τ²-Bench Telecom89.5%86.5%Claude Opus 4.5
METR time horizons75.0%69.6%Claude Opus 4.5
Remote Labor Index3.8%1.7%Claude Opus 4.5
GDPval45.5%34.8%Claude Opus 4.5
BALROG43.5%32.8%Claude Opus 4.5
DeepResearch Bench54.8%49.6%Claude Opus 4.5
OSWorld66.3%Not measuredOnly Claude Opus 4.5 measured
Vending-Bench 2$4,967Not measuredOnly Claude Opus 4.5 measured
Berkeley Function Calling Leaderboard (BFCL)77.5%Not measuredOnly Claude Opus 4.5 measured
BrowseComp-PlusNot measured80.0%Only GPT-5 measured
Neither model has a result on the other 27 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index124
Reasoning benchmarks for Claude Opus 4.5 and GPT-5
BenchmarkClaude Opus 4.5GPT-5Leader
GPQA Diamond85.9%85.6%Claude Opus 4.5
MMMU Pro (Vals AI)83.0%81.5%Claude Opus 4.5
GPQA Diamond (Artificial Analysis run)86.6%85.4%Claude Opus 4.5
Humanity's Last Exam (Artificial Analysis run)30.1%28.5%Claude Opus 4.5
GPQA Diamond (Epoch AI run)86.0%86.2%GPT-5
ARC-AGI80.0%65.7%Claude Opus 4.5
ARC-AGI-237.6%9.9%Claude Opus 4.5
SimpleBench62.0%56.7%Claude Opus 4.5
Chess puzzles14.0%36.0%GPT-5
Mystery game puzzles22.0%23.0%GPT-5
EBR-bench14.3%12.7%Claude Opus 4.5
VPCT40.0%66.0%GPT-5
LMArena Text: hard prompts14761415Claude Opus 4.5
LMArena Text: expert14871419Claude Opus 4.5
LMArena Text: hard prompts in English14821419Claude Opus 4.5
LMArena Vision: diagramsNot measured1252Only GPT-5 measured
LMArena Vision: homeworkNot measured1278Only GPT-5 measured
Kagi LLM Benchmark80.2%72.7%Claude Opus 4.5
Neither model has a result on the other 4 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index55
Math benchmarks for Claude Opus 4.5 and GPT-5
BenchmarkClaude Opus 4.5GPT-5Leader
AIME95.4%93.4%Claude Opus 4.5
MATH 500 (Vals AI)Not measured96.0%Only GPT-5 measured
MGSM (Vals AI)95.2%92.8%Claude Opus 4.5
AA Math Index91.394.3GPT-5
AIME 2025 (Artificial Analysis run)91.3%94.3%GPT-5
OTIS Mock AIME86.1%91.4%GPT-5
FrontierMath, tiers 1 to 334.4%55.4%GPT-5
FrontierMath, tier 44.9%22.0%GPT-5
ProofBench36.0%18.0%Claude Opus 4.5
MATH level 5Not measured98.1%Only GPT-5 measured
LMArena Text: math14631407Claude Opus 4.5
LMArena Text: mathematical work14681405Claude Opus 4.5
Neither model has a result on the other 1 board here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index97
Knowledge benchmarks for Claude Opus 4.5 and GPT-5
BenchmarkClaude Opus 4.5GPT-5Leader
MMLU Pro87.3%86.5%Claude Opus 4.5
LegalBench (Vals AI)84.6%86.0%GPT-5
CaseLaw (Vals AI)62.6%66.5%GPT-5
CorpFin (Vals AI)65.1%61.1%Claude Opus 4.5
TaxEval (Vals AI)74.9%73.4%Claude Opus 4.5
MortgageTax (Vals AI)68.7%65.5%Claude Opus 4.5
MedQA (Vals AI)95.9%96.3%GPT-5
MedCode (Vals AI)49.2%49.6%GPT-5
MMLU Pro (Artificial Analysis run)89.5%87.1%Claude Opus 4.5
SimpleQA Verified45.7%50.1%GPT-5
GeoBench75.0%81.0%GPT-5
LMArena Text: science14541416Claude Opus 4.5
LMArena Text: medicine and healthcare14441413Claude Opus 4.5
LMArena Text: legal and government14591431Claude Opus 4.5
LMArena Text: business and finance14481400Claude Opus 4.5
FACTS Benchmark Suite43.9%56.5%GPT-5
Neither model has a result on the other 2 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index71
Web design benchmarks for Claude Opus 4.5 and GPT-5
BenchmarkClaude Opus 4.5GPT-5Leader
Design Arena: websites12471184Claude Opus 4.5
Design Arena: UI components12351177Claude Opus 4.5
Design Arena: game dev12281185Claude Opus 4.5
Design Arena: data viz12431221Claude Opus 4.5
Design Arena: 3D12131055Claude Opus 4.5
Design Arena: all code categories12421167Claude Opus 4.5
Design Arena: SVG11801188GPT-5
Design Arena: ASCII art11901141Claude Opus 4.5
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index203
General benchmarks for Claude Opus 4.5 and GPT-5
BenchmarkClaude Opus 4.5GPT-5Leader
SAGE (Vals AI)52.1%43.7%Claude Opus 4.5
MedScribe (Vals AI)85.3%83.7%Claude Opus 4.5
IFBench58.0%73.1%GPT-5
Long context reasoning (AA-LCR)77.3%78.2%GPT-5
DTBench89.9%90.7%GPT-5
LMCA44.5%40.0%Claude Opus 4.5
Fiction.LiveBenchNot measured97.2%Only GPT-5 measured
Creative writing (Lech Mazur)Not measured86.0%Only GPT-5 measured
CL-bench21.1%Not measuredOnly Claude Opus 4.5 measured
Furniture assembly28.3%Not measuredOnly Claude Opus 4.5 measured
LMArena Text14511406Claude Opus 4.5
LMArena Text: instruction following14781388Claude Opus 4.5
LMArena Text: creative writing14451365Claude Opus 4.5
LMArena VisionNot measured1232Only GPT-5 measured
LMArena Text: English14611409Claude Opus 4.5
LMArena Text: non-English14381397Claude Opus 4.5
LMArena Text: Chinese14701422Claude Opus 4.5
LMArena Text: German14491416Claude Opus 4.5
LMArena Text: Japanese14171409Claude Opus 4.5
LMArena Text: Korean14241360Claude Opus 4.5
LMArena Text: French14711409Claude Opus 4.5
LMArena Text: Spanish14571399Claude Opus 4.5
LMArena Text: Russian14471407Claude Opus 4.5
LMArena Text: Polish14391431Claude Opus 4.5
LMArena Text: multi-turn14661426Claude Opus 4.5
LMArena Text: longer queries14791399Claude Opus 4.5
LMArena Text: writing and language14521384Claude Opus 4.5
LMArena Text: entertainment and media14341379Claude Opus 4.5
LMArena Vision: EnglishNot measured1231Only GPT-5 measured
LMArena Vision: ChineseNot measured1267Only GPT-5 measured
LMArena Vision: reading textNot measured1246Only GPT-5 measured
LMArena Vision: humorNot measured1219Only GPT-5 measured
LMArena Vision: captioningNot measured1212Only GPT-5 measured
LMArena Vision: recognizing thingsNot measured1263Only GPT-5 measured
LMArena Vision: creative writingNot measured1210Only GPT-5 measured
LMArena Document1462Not measuredOnly Claude Opus 4.5 measured
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 4.5 and GPT-5
BenchmarkClaude Opus 4.5GPT-5Leader
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$0.0063Fits in one request

GPT-5 costs less

Repository review

50K input + 3K output tokens

Claude Opus 4.5$0.325Fits in one request
GPT-5$0.092Fits in one request

GPT-5 costs less

Agent loop

200K input + 10K output tokens

Claude Opus 4.5$1.25Exceeds the context window
GPT-5$0.350Fits in one request

GPT-5 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
SpecificationAnthropic Claude Opus 4.5OpenAI GPT-5
MakerAnthropicOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedNovember 24, 2025August 7, 2025
Context window200K400K
Input $/Mtok$5.00$1.25
Output $/Mtok$25.00$10.00
Coding index44.038.8
Independent measurements behind it33
Cost per solved task$1.37$0.39
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Opus 4.5 better than GPT-5 for coding?

Pick Claude Opus 4.5 for coding: it scores 44.0 on the Vibe Coding Index against 38.8 for GPT-5. Pick GPT-5 for output tokens 2.5x cheaper ($10.00 vs $25.00 per million) and a lower cost per solved task ($0.39 against $1.37).

Which is cheaper, Claude Opus 4.5 or GPT-5?

Claude Opus 4.5 costs $5.00 per million input tokens and $25.00 per million output tokens; GPT-5 costs $1.25 and $10.00. Per solved SWE-bench Verified task, Claude Opus 4.5 costs $1.37 and GPT-5 $0.39.

Which has the bigger context window, Claude Opus 4.5 or GPT-5?

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

How many benchmarks is the Claude Opus 4.5 vs GPT-5 comparison based on?

94 benchmarks have a result for both models as of October 22, 2026. Claude Opus 4.5's coding index rests on 3 independent benchmarks and GPT-5'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-4-5-vs-gpt-5" title="Claude Opus 4.5 vs GPT-5, 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-4-5-vs-gpt-5">LLMBenchmark.ai, Claude Opus 4.5 vs GPT-5</a></p>