Enter opens the highlighted result. Esc closes.

Claude Opus 4.8 vs GPT-5

Claude Opus 4.8 leads GPT-5 on coding, 65.0 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; 89 benchmarks have a result for both.

Replace Claude Opus 4.8 Replace GPT-5
Claude Opus 4.8Anthropic
Coding
65.0
Overall
69.8
Output $/M
$25.00
85
GPT-5OpenAI
Coding
38.8
Overall
51.5
Output $/M
$10.00
4
vs boards won of 89 shared

Claude Opus 4.8 or GPT-5: which to pick

Pick Claude Opus 4.8 for coding: it scores 65.0 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 $2.17).

Model AClaude Opus 4.8Anthropic65.0/1006 independent benchmarks$2.17 per solved taskModel BGPT-5OpenAI38.8/1003 independent benchmarks$0.39 per solved task
Shared results
89
Claude Opus 4.8 only
41
GPT-5 only
24
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 4.8 65.0 from 6 benchmarks, GPT-5 38.8 from 3 benchmarks.
Widest category
Math, 24.2 points apart on average over 6 shared benchmarks.
Widest single gap
Vibe Code Bench (Vals AI): Claude Opus 4.8 82.7% against GPT-5 20.1%, 62.6 points apart on a 0 to 100 scale.
Output price
Claude Opus 4.8 $25.00 against GPT-5 $10.00 per million output tokens, 2.5x apart.
Context window
Claude Opus 4.8 takes 1M 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 4.8BarsGPT-5Ties
Coding120
Intelligence20
Agentic work30
Reasoning170
Math60
Knowledge102
Web design80
General272
All shared boards854
CodingLike-for-likeSix of these boards feed the Vibe Coding Index120
Coding benchmarks for Claude Opus 4.8 and GPT-5
BenchmarkClaude Opus 4.8GPT-5Leader
Aider polyglotNot measured88.0%Only GPT-5 measured
SWE-bench VerifiedNot measured74.4%Only GPT-5 measured
LiveBench coding77.3%Not measuredOnly Claude Opus 4.8 measured
LMArena WebDev15561418Claude Opus 4.8
AA Coding Index74.337.8Claude Opus 4.8
LiveCodeBench (Vals AI)87.8%85.9%Claude Opus 4.8
SWE-bench Verified (Vals AI)88.6%69.0%Claude Opus 4.8
Terminal-Bench 4 (Vals AI)23.2%Not measuredOnly Claude Opus 4.8 measured
Vibe Code Bench (Vals AI)82.7%20.1%Claude Opus 4.8
Code migration (Vals AI)47.3%Not measuredOnly Claude Opus 4.8 measured
ProgramBench (Vals AI)1.0%Not measuredOnly Claude Opus 4.8 measured
Terminal-Bench 2.1 (Vals AI)71.9%Not measuredOnly Claude Opus 4.8 measured
SkillsBench (Vals AI)59.2%Not measuredOnly Claude Opus 4.8 measured
LiveCodeBench (Artificial Analysis run)Not measured84.6%Only GPT-5 measured
SciCode54.4%Not measuredOnly Claude Opus 4.8 measured
Terminal-Bench Hard (Artificial Analysis run)58.3%37.9%Claude Opus 4.8
Terminal-BenchNot measured49.6%Only GPT-5 measured
FrontierCode46.5%Not measuredOnly Claude Opus 4.8 measured
GSO-Bench47.1%6.9%Claude Opus 4.8
WeirdML82.9%60.7%Claude Opus 4.8
ALE-BenchNot measured807.6Only GPT-5 measured
LMArena Text: coding14901436Claude Opus 4.8
LMArena Text: software and IT14881420Claude Opus 4.8
LMArena WebDev: React1557Not measuredOnly Claude Opus 4.8 measured
LMArena WebDev: HTML15431427Claude Opus 4.8
SciCode12.3%0.0%Claude Opus 4.8
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 4.8 and GPT-5
BenchmarkClaude Opus 4.8GPT-5Leader
AA Intelligence Index41.823.0Claude Opus 4.8
Epoch Capabilities Index159.0150.0Claude Opus 4.8
Agentic workLike-for-likePublic boards, shown as published, kept out of the index30
Agentic work benchmarks for Claude Opus 4.8 and GPT-5
BenchmarkClaude Opus 4.8GPT-5Leader
AA Agentic Index41.9Not measuredOnly Claude Opus 4.8 measured
Design Arena: agents building web apps1233Not measuredOnly Claude Opus 4.8 measured
Design Arena: agents building full-stack apps1249Not measuredOnly Claude Opus 4.8 measured
Design Arena: agents building mobile apps1222Not measuredOnly Claude Opus 4.8 measured
Design Arena: agents building Android apps1233Not measuredOnly Claude Opus 4.8 measured
Design Arena: agents building Godot games1231Not measuredOnly Claude Opus 4.8 measured
Design Arena: agents building games1239Not measuredOnly Claude Opus 4.8 measured
Design Arena: HTML slides1171Not measuredOnly Claude Opus 4.8 measured
Design Arena: PowerPoint slides1202Not measuredOnly Claude Opus 4.8 measured
Design Arena: spreadsheets1303Not measuredOnly Claude Opus 4.8 measured
LiveBench research81.8%Not measuredOnly Claude Opus 4.8 measured
LiveBench browser96.0%Not measuredOnly Claude Opus 4.8 measured
LiveBench long agentic48.3%Not measuredOnly Claude Opus 4.8 measured
Finance Agent (Vals AI)53.9%Not measuredOnly Claude Opus 4.8 measured
Tax Agent Bench (Vals AI)30.0%Not measuredOnly Claude Opus 4.8 measured
Legal Research Bench (Vals AI)43.8%Not measuredOnly Claude Opus 4.8 measured
Excel Modeling Benchmark (Vals AI)69.4%Not measuredOnly Claude Opus 4.8 measured
Terminal-Bench-Science (Vals AI)4.3%Not measuredOnly Claude Opus 4.8 measured
Time Horizon Index (Vals AI)11.8%Not measuredOnly Claude Opus 4.8 measured
τ²-Bench Telecom94.4%86.5%Claude Opus 4.8
APEX-Agents48.9%Not measuredOnly Claude Opus 4.8 measured
METR time horizonsNot measured69.6%Only GPT-5 measured
Remote Labor Index8.3%1.7%Claude Opus 4.8
GDPvalNot measured34.8%Only GPT-5 measured
OSWorld 2.020.6%Not measuredOnly Claude Opus 4.8 measured
BALROGNot measured32.8%Only GPT-5 measured
DeepResearch Bench50.2%49.6%Claude Opus 4.8
PostTrainBench33.8%Not measuredOnly Claude Opus 4.8 measured
Vending-Bench 2$5,787Not measuredOnly Claude Opus 4.8 measured
LMArena Search1204Not measuredOnly Claude Opus 4.8 measured
BrowseComp-PlusNot measured80.0%Only GPT-5 measured
Neither model has a result on the other 10 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index170
Reasoning benchmarks for Claude Opus 4.8 and GPT-5
BenchmarkClaude Opus 4.8GPT-5Leader
GPQA Diamond92.4%85.6%Claude Opus 4.8
LiveBench reasoning89.2%Not measuredOnly Claude Opus 4.8 measured
MMMU Pro (Vals AI)86.6%81.5%Claude Opus 4.8
GPQA Diamond (Artificial Analysis run)92.0%85.4%Claude Opus 4.8
Humanity's Last Exam (Artificial Analysis run)48.7%28.5%Claude Opus 4.8
GPQA Diamond (Epoch AI run)91.0%86.2%Claude Opus 4.8
ARC-AGI92.5%65.7%Claude Opus 4.8
ARC-AGI-272.1%9.9%Claude Opus 4.8
SimpleBench64.8%56.7%Claude Opus 4.8
Chess puzzles52.0%36.0%Claude Opus 4.8
Mystery game puzzles36.0%23.0%Claude Opus 4.8
EBR-bench28.6%12.7%Claude Opus 4.8
VPCTNot measured66.0%Only GPT-5 measured
LMArena Text: hard prompts14821415Claude Opus 4.8
LMArena Text: expert15031419Claude Opus 4.8
LMArena Text: hard prompts in English14871419Claude Opus 4.8
LMArena Vision: diagrams13151252Claude Opus 4.8
LMArena Vision: homework13371278Claude Opus 4.8
Kagi LLM Benchmark88.8%72.7%Claude Opus 4.8
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 4.8 and GPT-5
BenchmarkClaude Opus 4.8GPT-5Leader
AIMENot measured93.4%Only GPT-5 measured
MATH 500 (Vals AI)Not measured96.0%Only GPT-5 measured
MGSM (Vals AI)Not measured92.8%Only GPT-5 measured
AA Math IndexNot measured94.3Only GPT-5 measured
AIME 2025 (Artificial Analysis run)Not measured94.3%Only GPT-5 measured
OTIS Mock AIME98.3%91.4%Claude Opus 4.8
FrontierMath, tiers 1 to 380.0%55.4%Claude Opus 4.8
FrontierMath, tier 456.1%22.0%Claude Opus 4.8
ProofBench69.0%18.0%Claude Opus 4.8
MATH level 5Not measured98.1%Only GPT-5 measured
LMArena Text: math14861407Claude Opus 4.8
LMArena Text: mathematical work14971405Claude Opus 4.8
Neither model has a result on the other 1 board here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index102
Knowledge benchmarks for Claude Opus 4.8 and GPT-5
BenchmarkClaude Opus 4.8GPT-5Leader
MMLU Pro89.6%86.5%Claude Opus 4.8
LegalBench (Vals AI)83.6%86.0%GPT-5
CaseLaw (Vals AI)Not measured66.5%Only GPT-5 measured
CorpFin (Vals AI)66.7%61.1%Claude Opus 4.8
TaxEval (Vals AI)75.6%73.4%Claude Opus 4.8
MortgageTax (Vals AI)69.9%65.5%Claude Opus 4.8
MedQA (Vals AI)Not measured96.3%Only GPT-5 measured
MedCode (Vals AI)53.2%49.6%Claude Opus 4.8
MMLU Pro (Artificial Analysis run)Not measured87.1%Only GPT-5 measured
SimpleQA Verified53.0%50.1%Claude Opus 4.8
GeoBenchNot measured81.0%Only GPT-5 measured
LMArena Text: science14771416Claude Opus 4.8
LMArena Text: medicine and healthcare14641413Claude Opus 4.8
LMArena Text: legal and government14771431Claude Opus 4.8
LMArena Text: business and finance14581400Claude Opus 4.8
FACTS Benchmark Suite53.5%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 index80
Web design benchmarks for Claude Opus 4.8 and GPT-5
BenchmarkClaude Opus 4.8GPT-5Leader
Design Arena: websites12581184Claude Opus 4.8
Design Arena: UI components12551177Claude Opus 4.8
Design Arena: game dev12641185Claude Opus 4.8
Design Arena: data viz12401221Claude Opus 4.8
Design Arena: 3D12221055Claude Opus 4.8
Design Arena: all code categories12551167Claude Opus 4.8
Design Arena: SVG11951188Claude Opus 4.8
Design Arena: ASCII art12771141Claude Opus 4.8
LiveBench design78.8%Not measuredOnly Claude Opus 4.8 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index272
General benchmarks for Claude Opus 4.8 and GPT-5
BenchmarkClaude Opus 4.8GPT-5Leader
LiveBench data analysis66.0%Not measuredOnly Claude Opus 4.8 measured
Public Benefits Bench (Vals AI)68.1%Not measuredOnly Claude Opus 4.8 measured
SAGE (Vals AI)54.8%43.7%Claude Opus 4.8
MedScribe (Vals AI)85.8%83.7%Claude Opus 4.8
Vals Multimodal Index70.9%Not measuredOnly Claude Opus 4.8 measured
IFBench62.2%73.1%GPT-5
Long context reasoning (AA-LCR)77.7%78.2%GPT-5
DTBench94.9%90.7%Claude Opus 4.8
LMCA57.5%40.0%Claude Opus 4.8
Fiction.LiveBenchNot measured97.2%Only GPT-5 measured
Creative writing (Lech Mazur)Not measured86.0%Only GPT-5 measured
Surface Evolver Bench87.5%Not measuredOnly Claude Opus 4.8 measured
Furniture assembly42.5%Not measuredOnly Claude Opus 4.8 measured
LMArena Text14611406Claude Opus 4.8
LMArena Text: instruction following14761388Claude Opus 4.8
LMArena Text: creative writing14541365Claude Opus 4.8
LMArena Vision12941232Claude Opus 4.8
LMArena Text: English14681409Claude Opus 4.8
LMArena Text: non-English14501397Claude Opus 4.8
LMArena Text: Chinese15061422Claude Opus 4.8
LMArena Text: German14721416Claude Opus 4.8
LMArena Text: Japanese14421409Claude Opus 4.8
LMArena Text: Korean14311360Claude Opus 4.8
LMArena Text: French14811409Claude Opus 4.8
LMArena Text: Spanish14651399Claude Opus 4.8
LMArena Text: Russian14741407Claude Opus 4.8
LMArena Text: Polish14591431Claude Opus 4.8
LMArena Text: multi-turn14761426Claude Opus 4.8
LMArena Text: longer queries14831399Claude Opus 4.8
LMArena Text: writing and language14611384Claude Opus 4.8
LMArena Text: entertainment and media14401379Claude Opus 4.8
LMArena Vision: English12931231Claude Opus 4.8
LMArena Vision: Chinese13461267Claude Opus 4.8
LMArena Vision: reading text13031246Claude Opus 4.8
LMArena Vision: humor12821219Claude Opus 4.8
LMArena Vision: captioningNot measured1212Only GPT-5 measured
LMArena Vision: recognizing thingsNot measured1263Only GPT-5 measured
LMArena Vision: creative writing13011210Claude Opus 4.8
LMArena Document1475Not measuredOnly Claude Opus 4.8 measured
Neither model has a result on the other 7 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Claude Opus 4.8 and GPT-5
BenchmarkClaude Opus 4.8GPT-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 4.8$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 4.8$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 4.8$1.25Fits in one request
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 4.8 and GPT-5
SpecificationAnthropic Claude Opus 4.8OpenAI GPT-5
MakerAnthropicOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedMay 27, 2026August 7, 2025
Context window1M400K
Input $/Mtok$5.00$1.25
Output $/Mtok$25.00$10.00
Coding index65.038.8
Independent measurements behind it63
Cost per solved task$2.17$0.39
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Opus 4.8 better than GPT-5 for coding?

Pick Claude Opus 4.8 for coding: it scores 65.0 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 $2.17).

Which is cheaper, Claude Opus 4.8 or GPT-5?

Claude Opus 4.8 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 4.8 costs $2.17 and GPT-5 $0.39.

Which has the bigger context window, Claude Opus 4.8 or GPT-5?

Claude Opus 4.8, with 1M tokens against 400K.

How many benchmarks is the Claude Opus 4.8 vs GPT-5 comparison based on?

89 benchmarks have a result for both models as of October 22, 2026. Claude Opus 4.8's coding index rests on 6 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-4-8-vs-gpt-5" title="Claude Opus 4.8 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-4-8-vs-gpt-5">LLMBenchmark.ai, Claude Opus 4.8 vs GPT-5</a></p>