Enter opens the highlighted result. Esc closes.

Claude Sonnet 4.5 vs GPT-5

Claude Sonnet 4.5 leads GPT-5 on coding, 39.5 to 38.8 on the Vibe Coding Index, and GPT-5 costs 1.5x less per output token ($10.00 vs $15.00 per million). Updated October 21, 2026; 84 benchmarks have a result for both.

Replace Claude Sonnet 4.5 Replace GPT-5
Claude Sonnet 4.5Anthropic
Coding
39.5
Overall
49.5
Output $/M
$15.00
44
GPT-5OpenAI
Coding
38.8
Overall
51.5
Output $/M
$10.00
40
vs boards won of 84 shared

Claude Sonnet 4.5 or GPT-5: which to pick

Claude Sonnet 4.5 and GPT-5 are level for coding, 39.5 against 38.8 on the Vibe Coding Index, so price and context decide.

Pick GPT-5 for output tokens 1.5x cheaper ($10.00 vs $15.00 per million) and a lower cost per solved task ($0.39 against $1.16). Pick Claude Sonnet 4.5 for a larger context window (1M against 400K tokens) and work measured by SWE-bench Verified or AA Coding Index, where it leads.

Model AClaude Sonnet 4.5Anthropic39.5/1003 independent benchmarks$1.16 per solved taskModel BGPT-5OpenAI38.8/1003 independent benchmarks$0.39 per solved task
Shared results
84
Claude Sonnet 4.5 only
11
GPT-5 only
29
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 Sonnet 4.5 39.5 from 3 benchmarks, GPT-5 38.8 from 3 benchmarks.
Widest category
Math, 9.9 points apart on average over 9 shared benchmarks.
Widest single gap
FrontierMath, tiers 1 to 3: Claude Sonnet 4.5 23.9% against GPT-5 55.4%, 31.6 points apart on a 0 to 100 scale.
Output price
Claude Sonnet 4.5 $15.00 against GPT-5 $10.00 per million output tokens, 1.5x apart.
Context window
Claude Sonnet 4.5 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 Sonnet 4.5BarsGPT-5Ties
Coding75
Intelligence02
Agentic work31
Reasoning410
Math45
Knowledge68
Web design44
General165
All shared boards4440
CodingLike-for-likeSix of these boards feed the Vibe Coding Index75
Coding benchmarks for Claude Sonnet 4.5 and GPT-5
BenchmarkClaude Sonnet 4.5GPT-5Leader
Aider polyglotNot measured88.0%Only GPT-5 measured
SWE-bench Verified74.8%74.4%Claude Sonnet 4.5
SWE-bench Multilingual67.0%Not measuredOnly Claude Sonnet 4.5 measured
LMArena WebDev13941418GPT-5
AA Coding Index52.137.8Claude Sonnet 4.5
LiveCodeBench (Vals AI)73.0%85.9%GPT-5
SWE-bench Verified (Vals AI)70.0%69.0%Claude Sonnet 4.5
Vibe Code Bench (Vals AI)22.6%20.1%Claude Sonnet 4.5
LiveCodeBench (Artificial Analysis run)Not measured84.6%Only GPT-5 measured
Terminal-Bench Hard (Artificial Analysis run)Not measured37.9%Only GPT-5 measured
Terminal-Bench46.5%49.6%GPT-5
GSO-Bench14.7%6.9%Claude Sonnet 4.5
WeirdML47.7%60.7%GPT-5
Cybench60.0%Not measuredOnly Claude Sonnet 4.5 measured
ALE-BenchNot measured807.6Only GPT-5 measured
LMArena Text: coding14881436Claude Sonnet 4.5
LMArena Text: software and IT14731420Claude Sonnet 4.5
LMArena WebDev: React1386Not measuredOnly Claude Sonnet 4.5 measured
LMArena WebDev: HTML13991427GPT-5
SciCodeNot measured0.0%Only GPT-5 measured
Neither model has a result on the other 19 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Claude Sonnet 4.5 and GPT-5
BenchmarkClaude Sonnet 4.5GPT-5Leader
AA Intelligence Index20.723.0GPT-5
Epoch Capabilities Index146.7150.0GPT-5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index31
Agentic work benchmarks for Claude Sonnet 4.5 and GPT-5
BenchmarkClaude Sonnet 4.5GPT-5Leader
AA Agentic Index15.8Not measuredOnly Claude Sonnet 4.5 measured
Design Arena: agents building web apps1059Not measuredOnly Claude Sonnet 4.5 measured
Design Arena: agents building full-stack apps1050Not measuredOnly Claude Sonnet 4.5 measured
Design Arena: agents building mobile apps1137Not measuredOnly Claude Sonnet 4.5 measured
τ²-Bench TelecomNot measured86.5%Only GPT-5 measured
METR time horizons67.4%69.6%GPT-5
Remote Labor Index2.1%1.7%Claude Sonnet 4.5
GDPval42.5%34.8%Claude Sonnet 4.5
BALROGNot measured32.8%Only GPT-5 measured
DeepResearch Bench52.6%49.6%Claude Sonnet 4.5
OSWorld62.9%Not measuredOnly Claude Sonnet 4.5 measured
Vending-Bench 2$3,839Not measuredOnly Claude Sonnet 4.5 measured
Berkeley Function Calling Leaderboard (BFCL)73.2%Not measuredOnly Claude Sonnet 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 index410
Reasoning benchmarks for Claude Sonnet 4.5 and GPT-5
BenchmarkClaude Sonnet 4.5GPT-5Leader
GPQA Diamond81.6%85.6%GPT-5
MMMU Pro (Vals AI)79.3%81.5%GPT-5
GPQA Diamond (Artificial Analysis run)Not measured85.4%Only GPT-5 measured
Humanity's Last Exam (Artificial Analysis run)Not measured28.5%Only GPT-5 measured
GPQA Diamond (Epoch AI run)82.3%86.2%GPT-5
ARC-AGI63.7%65.7%GPT-5
ARC-AGI-213.6%9.9%Claude Sonnet 4.5
SimpleBench54.3%56.7%GPT-5
Chess puzzles10.0%36.0%GPT-5
Mystery game puzzles17.0%23.0%GPT-5
EBR-bench2.4%12.7%GPT-5
VPCT39.8%66.0%GPT-5
LMArena Text: hard prompts14621415Claude Sonnet 4.5
LMArena Text: expert14831419Claude Sonnet 4.5
LMArena Text: hard prompts in English14711419Claude Sonnet 4.5
LMArena Vision: diagramsNot measured1252Only GPT-5 measured
LMArena Vision: homeworkNot measured1278Only GPT-5 measured
Kagi LLM Benchmark57.9%72.7%GPT-5
Neither model has a result on the other 4 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index45
Math benchmarks for Claude Sonnet 4.5 and GPT-5
BenchmarkClaude Sonnet 4.5GPT-5Leader
AIME88.2%93.4%GPT-5
MATH 500 (Vals AI)Not measured96.0%Only GPT-5 measured
MGSM (Vals AI)94.3%92.8%Claude Sonnet 4.5
AA Math IndexNot measured94.3Only GPT-5 measured
AIME 2025 (Artificial Analysis run)Not measured94.3%Only GPT-5 measured
OTIS Mock AIME77.8%91.4%GPT-5
FrontierMath, tiers 1 to 323.9%55.4%GPT-5
FrontierMath, tier 42.4%22.0%GPT-5
ProofBench19.0%18.0%Claude Sonnet 4.5
MATH level 597.7%98.1%GPT-5
LMArena Text: math14491407Claude Sonnet 4.5
LMArena Text: mathematical work14621405Claude Sonnet 4.5
Neither model has a result on the other 1 board here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index68
Knowledge benchmarks for Claude Sonnet 4.5 and GPT-5
BenchmarkClaude Sonnet 4.5GPT-5Leader
MMLU Pro87.4%86.5%Claude Sonnet 4.5
LegalBench (Vals AI)84.1%86.0%GPT-5
CaseLaw (Vals AI)62.2%66.5%GPT-5
CorpFin (Vals AI)62.0%61.1%Claude Sonnet 4.5
TaxEval (Vals AI)73.3%73.4%GPT-5
MortgageTax (Vals AI)64.0%65.5%GPT-5
MedQA (Vals AI)94.7%96.3%GPT-5
MedCode (Vals AI)44.1%49.6%GPT-5
MMLU Pro (Artificial Analysis run)Not measured87.1%Only GPT-5 measured
SimpleQA Verified30.7%50.1%GPT-5
GeoBenchNot measured81.0%Only GPT-5 measured
LMArena Text: science14481416Claude Sonnet 4.5
LMArena Text: medicine and healthcare14441413Claude Sonnet 4.5
LMArena Text: legal and government14511431Claude Sonnet 4.5
LMArena Text: business and finance14401400Claude Sonnet 4.5
FACTS Benchmark Suite40.6%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 index44
Web design benchmarks for Claude Sonnet 4.5 and GPT-5
BenchmarkClaude Sonnet 4.5GPT-5Leader
Design Arena: websites11901184Claude Sonnet 4.5
Design Arena: UI components11731180GPT-5
Design Arena: game dev11661185GPT-5
Design Arena: data viz11671221GPT-5
Design Arena: 3D11581056Claude Sonnet 4.5
Design Arena: all code categories11831168Claude Sonnet 4.5
Design Arena: SVG11151189GPT-5
Design Arena: ASCII art12051141Claude Sonnet 4.5
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index165
General benchmarks for Claude Sonnet 4.5 and GPT-5
BenchmarkClaude Sonnet 4.5GPT-5Leader
SAGE (Vals AI)36.1%43.7%GPT-5
MedScribe (Vals AI)84.5%83.7%Claude Sonnet 4.5
IFBenchNot measured73.1%Only GPT-5 measured
Long context reasoning (AA-LCR)Not measured78.2%Only GPT-5 measured
DTBench83.2%90.7%GPT-5
LMCA38.8%40.0%GPT-5
Fiction.LiveBenchNot measured97.2%Only GPT-5 measured
Creative writing (Lech Mazur)Not measured86.0%Only GPT-5 measured
LMArena Text14381406Claude Sonnet 4.5
LMArena Text: instruction following14591388Claude Sonnet 4.5
LMArena Text: creative writing14421365Claude Sonnet 4.5
LMArena VisionNot measured1232Only GPT-5 measured
LMArena Text: English14501409Claude Sonnet 4.5
LMArena Text: non-English14251397Claude Sonnet 4.5
LMArena Text: Chinese14601422Claude Sonnet 4.5
LMArena Text: German14271416Claude Sonnet 4.5
LMArena Text: Japanese13901409GPT-5
LMArena Text: Korean14021360Claude Sonnet 4.5
LMArena Text: French14591409Claude Sonnet 4.5
LMArena Text: Spanish14581399Claude Sonnet 4.5
LMArena Text: Russian14371407Claude Sonnet 4.5
LMArena Text: Polish14231431GPT-5
LMArena Text: multi-turn14651426Claude Sonnet 4.5
LMArena Text: longer queries14751399Claude Sonnet 4.5
LMArena Text: writing and language14421384Claude Sonnet 4.5
LMArena Text: entertainment and media14281379Claude Sonnet 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 Document1450Not measuredOnly Claude Sonnet 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 Sonnet 4.5 and GPT-5
BenchmarkClaude Sonnet 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 Sonnet 4.5$0.011Fits in one request
GPT-5$0.0063Fits in one request

GPT-5 costs less

Repository review

50K input + 3K output tokens

Claude Sonnet 4.5$0.195Fits in one request
GPT-5$0.092Fits in one request

GPT-5 costs less

Agent loop

200K input + 10K output tokens

Claude Sonnet 4.5$0.750Fits 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 Sonnet 4.5 and GPT-5
SpecificationAnthropic Claude Sonnet 4.5OpenAI GPT-5
MakerAnthropicOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedSeptember 29, 2025August 7, 2025
Context window1M400K
Input $/Mtok$3.00$1.25
Output $/Mtok$15.00$10.00
Coding index39.538.8
Independent measurements behind it33
Cost per solved task$1.16$0.39
SourceOpenRouter listingOpenRouter listing

Questions

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

Claude Sonnet 4.5 and GPT-5 are level for coding, 39.5 against 38.8 on the Vibe Coding Index, so price and context decide. Pick GPT-5 for output tokens 1.5x cheaper ($10.00 vs $15.00 per million) and a lower cost per solved task ($0.39 against $1.16). Pick Claude Sonnet 4.5 for a larger context window (1M against 400K tokens) and work measured by SWE-bench Verified or AA Coding Index, where it leads.

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

Claude Sonnet 4.5 costs $3.00 per million input tokens and $15.00 per million output tokens; GPT-5 costs $1.25 and $10.00. Per solved SWE-bench Verified task, Claude Sonnet 4.5 costs $1.16 and GPT-5 $0.39.

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

Claude Sonnet 4.5, with 1M tokens against 400K.

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

84 benchmarks have a result for both models as of October 21, 2026. Claude Sonnet 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-sonnet-4-5-vs-gpt-5" title="Claude Sonnet 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-sonnet-4-5-vs-gpt-5">LLMBenchmark.ai, Claude Sonnet 4.5 vs GPT-5</a></p>