Enter opens the highlighted result. Esc closes.

Claude Sonnet 4.5 vs GPT-5.2

GPT-5.2 leads Claude Sonnet 4.5 on coding, 55.9 to 39.5 on the Vibe Coding Index, at about the same output price ($14.00 vs $15.00 per million). Updated October 21, 2026; 89 benchmarks have a result for both.

Replace Claude Sonnet 4.5 Replace GPT-5.2
Claude Sonnet 4.5Anthropic
Coding
39.5
Overall
49.5
Output $/M
$15.00
43
GPT-5.2OpenAI
Coding
55.9
Overall
60.7
Output $/M
$14.00
46
vs boards won of 89 shared

Claude Sonnet 4.5 or GPT-5.2: which to pick

Pick GPT-5.2 for coding: it scores 55.9 on the Vibe Coding Index against 39.5 for Claude Sonnet 4.5.

Pick Claude Sonnet 4.5 for a lower cost per solved task ($1.16 against $1.91) and a larger context window (1M against 400K tokens).

Model AClaude Sonnet 4.5Anthropic39.5/1003 independent benchmarks$1.16 per solved taskModel BGPT-5.2OpenAI55.9/1003 independent benchmarks$1.91 per solved task
Shared results
89
Claude Sonnet 4.5 only
6
GPT-5.2 only
25
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-5.2 55.9 from 3 benchmarks.
Widest category
Reasoning, 17.1 points apart on average over 14 shared benchmarks.
Widest single gap
VPCT: Claude Sonnet 4.5 39.8% against GPT-5.2 84.0%, 44.2 points apart on a 0 to 100 scale.
Output price
Claude Sonnet 4.5 $15.00 against GPT-5.2 $14.00 per million output tokens, 1.1x apart.
Context window
Claude Sonnet 4.5 takes 1M tokens, GPT-5.2 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-5.2Ties
Coding48
Intelligence02
Agentic work54
Reasoning410
Math44
Knowledge77
Web design35
General166
All shared boards4346
CodingLike-for-likeSix of these boards feed the Vibe Coding Index48
Coding benchmarks for Claude Sonnet 4.5 and GPT-5.2
BenchmarkClaude Sonnet 4.5GPT-5.2Leader
SWE-bench Verified74.8%72.8%Claude Sonnet 4.5
SWE-bench Multilingual67.0%66.7%Claude Sonnet 4.5
LMArena WebDev13941417GPT-5.2
AA Coding Index52.1Not measuredOnly Claude Sonnet 4.5 measured
LiveCodeBench (Vals AI)73.0%85.4%GPT-5.2
SWE-bench Verified (Vals AI)70.0%75.8%GPT-5.2
Vibe Code Bench (Vals AI)22.6%53.5%GPT-5.2
LiveCodeBench (Artificial Analysis run)Not measured89.4%Only GPT-5.2 measured
Terminal-Bench Hard (Artificial Analysis run)Not measured47.0%Only GPT-5.2 measured
Terminal-Bench46.5%64.9%GPT-5.2
GSO-Bench14.7%27.5%GPT-5.2
WeirdML47.7%72.2%GPT-5.2
Cybench60.0%Not measuredOnly Claude Sonnet 4.5 measured
ALE-BenchNot measured1293.5Only GPT-5.2 measured
LMArena Text: coding14881442Claude Sonnet 4.5
LMArena Text: software and IT14731434Claude Sonnet 4.5
LMArena WebDev: React1386Not measuredOnly Claude Sonnet 4.5 measured
LMArena WebDev: HTML13991427GPT-5.2
Neither model has a result on the other 21 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Claude Sonnet 4.5 and GPT-5.2
BenchmarkClaude Sonnet 4.5GPT-5.2Leader
AA Intelligence Index20.730.4GPT-5.2
Epoch Capabilities Index146.7153.7GPT-5.2
Agentic workLike-for-likePublic boards, shown as published, kept out of the index54
Agentic work benchmarks for Claude Sonnet 4.5 and GPT-5.2
BenchmarkClaude Sonnet 4.5GPT-5.2Leader
AA Agentic Index15.8Not measuredOnly Claude Sonnet 4.5 measured
Design Arena: agents building web apps10591086GPT-5.2
Design Arena: agents building full-stack apps10501043Claude Sonnet 4.5
Design Arena: agents building mobile apps11371093Claude Sonnet 4.5
Design Arena: agents building Android appsNot measured1058Only GPT-5.2 measured
Design Arena: agents building Godot gamesNot measured1142Only GPT-5.2 measured
τ²-Bench TelecomNot measured84.8%Only GPT-5.2 measured
METR time horizons67.4%75.3%GPT-5.2
Remote Labor Index2.1%2.5%GPT-5.2
GDPval42.5%49.7%GPT-5.2
DeepResearch Bench52.6%41.1%Claude Sonnet 4.5
OSWorld62.9%Not measuredOnly Claude Sonnet 4.5 measured
Vending-Bench 2$3,839$3,591Claude Sonnet 4.5
Berkeley Function Calling Leaderboard (BFCL)73.2%55.9%Claude Sonnet 4.5
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-5.2
BenchmarkClaude Sonnet 4.5GPT-5.2Leader
GPQA Diamond81.6%91.7%GPT-5.2
MMMU Pro (Vals AI)79.3%86.7%GPT-5.2
GPQA Diamond (Artificial Analysis run)Not measured90.3%Only GPT-5.2 measured
Humanity's Last Exam (Artificial Analysis run)Not measured37.7%Only GPT-5.2 measured
GPQA Diamond (Epoch AI run)82.3%91.4%GPT-5.2
ARC-AGI63.7%86.2%GPT-5.2
ARC-AGI-213.6%52.9%GPT-5.2
SimpleBench54.3%45.8%Claude Sonnet 4.5
Chess puzzles10.0%48.0%GPT-5.2
Mystery game puzzles17.0%23.0%GPT-5.2
EBR-bench2.4%23.0%GPT-5.2
VPCT39.8%84.0%GPT-5.2
LMArena Text: hard prompts14621428Claude Sonnet 4.5
LMArena Text: expert14831445Claude Sonnet 4.5
LMArena Text: hard prompts in English14711431Claude Sonnet 4.5
LMArena Vision: diagramsNot measured1265Only GPT-5.2 measured
LMArena Vision: homeworkNot measured1276Only GPT-5.2 measured
Kagi LLM Benchmark57.9%73.3%GPT-5.2
Neither model has a result on the other 4 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index44
Math benchmarks for Claude Sonnet 4.5 and GPT-5.2
BenchmarkClaude Sonnet 4.5GPT-5.2Leader
AIME88.2%96.9%GPT-5.2
MGSM (Vals AI)94.3%94.0%Claude Sonnet 4.5
AA Math IndexNot measured99.0Only GPT-5.2 measured
AIME 2025 (Artificial Analysis run)Not measured99.0%Only GPT-5.2 measured
OTIS Mock AIME77.8%96.1%GPT-5.2
FrontierMath, tiers 1 to 323.9%67.4%GPT-5.2
FrontierMath, tier 42.4%31.7%GPT-5.2
ProofBench19.0%15.0%Claude Sonnet 4.5
MATH level 597.7%Not measuredOnly Claude Sonnet 4.5 measured
LMArena Text: math14491440Claude Sonnet 4.5
LMArena Text: mathematical work14621442Claude Sonnet 4.5
Neither model has a result on the other 2 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index77
Knowledge benchmarks for Claude Sonnet 4.5 and GPT-5.2
BenchmarkClaude Sonnet 4.5GPT-5.2Leader
MMLU Pro87.4%86.2%Claude Sonnet 4.5
LegalBench (Vals AI)84.1%82.8%Claude Sonnet 4.5
CaseLaw (Vals AI)62.2%66.0%GPT-5.2
CorpFin (Vals AI)62.0%65.9%GPT-5.2
TaxEval (Vals AI)73.3%75.8%GPT-5.2
MortgageTax (Vals AI)64.0%67.1%GPT-5.2
MedQA (Vals AI)94.7%94.1%Claude Sonnet 4.5
MedCode (Vals AI)44.1%49.8%GPT-5.2
MMLU Pro (Artificial Analysis run)Not measured87.4%Only GPT-5.2 measured
SimpleQA Verified30.7%37.1%GPT-5.2
LMArena Text: science14481425Claude Sonnet 4.5
LMArena Text: medicine and healthcare14441425Claude Sonnet 4.5
LMArena Text: legal and government14511427Claude Sonnet 4.5
LMArena Text: business and finance14401414Claude Sonnet 4.5
FACTS Benchmark Suite40.6%48.5%GPT-5.2
Neither model has a result on the other 3 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index35
Web design benchmarks for Claude Sonnet 4.5 and GPT-5.2
BenchmarkClaude Sonnet 4.5GPT-5.2Leader
Design Arena: websites11901195GPT-5.2
Design Arena: UI components11731190GPT-5.2
Design Arena: game dev11661195GPT-5.2
Design Arena: data viz11671202GPT-5.2
Design Arena: 3D11581079Claude Sonnet 4.5
Design Arena: all code categories11831170Claude Sonnet 4.5
Design Arena: SVG11151139GPT-5.2
Design Arena: ASCII art12051152Claude 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 index166
General benchmarks for Claude Sonnet 4.5 and GPT-5.2
BenchmarkClaude Sonnet 4.5GPT-5.2Leader
SAGE (Vals AI)36.1%49.3%GPT-5.2
MedScribe (Vals AI)84.5%84.4%Claude Sonnet 4.5
IFBenchNot measured75.4%Only GPT-5.2 measured
Long context reasoning (AA-LCR)Not measured82.7%Only GPT-5.2 measured
DTBench83.2%90.9%GPT-5.2
LMCA38.8%43.9%GPT-5.2
CL-benchNot measured18.2%Only GPT-5.2 measured
Furniture assemblyNot measured38.3%Only GPT-5.2 measured
LMArena Text14381416Claude Sonnet 4.5
LMArena Text: instruction following14591409Claude Sonnet 4.5
LMArena Text: creative writing14421376Claude Sonnet 4.5
LMArena VisionNot measured1246Only GPT-5.2 measured
LMArena Text: English14501422Claude Sonnet 4.5
LMArena Text: non-English14251405Claude Sonnet 4.5
LMArena Text: Chinese14601447Claude Sonnet 4.5
LMArena Text: German14271444GPT-5.2
LMArena Text: Japanese13901420GPT-5.2
LMArena Text: Korean14021374Claude Sonnet 4.5
LMArena Text: French14591454Claude Sonnet 4.5
LMArena Text: Spanish14581413Claude Sonnet 4.5
LMArena Text: Russian14371415Claude Sonnet 4.5
LMArena Text: Polish14231426GPT-5.2
LMArena Text: multi-turn14651419Claude Sonnet 4.5
LMArena Text: longer queries14751413Claude Sonnet 4.5
LMArena Text: writing and language14421392Claude Sonnet 4.5
LMArena Text: entertainment and media14281378Claude Sonnet 4.5
LMArena Vision: EnglishNot measured1243Only GPT-5.2 measured
LMArena Vision: ChineseNot measured1305Only GPT-5.2 measured
LMArena Vision: reading textNot measured1257Only GPT-5.2 measured
LMArena Vision: humorNot measured1227Only GPT-5.2 measured
LMArena Vision: captioningNot measured1267Only GPT-5.2 measured
LMArena Vision: recognizing thingsNot measured1232Only GPT-5.2 measured
LMArena Vision: creative writingNot measured1225Only GPT-5.2 measured
LMArena Document14501405Claude Sonnet 4.5
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-5.2
BenchmarkClaude Sonnet 4.5GPT-5.2Leader
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-5.2$0.0088Fits in one request

GPT-5.2 costs less

Repository review

50K input + 3K output tokens

Claude Sonnet 4.5$0.195Fits in one request
GPT-5.2$0.130Fits in one request

GPT-5.2 costs less

Agent loop

200K input + 10K output tokens

Claude Sonnet 4.5$0.750Fits in one request
GPT-5.2$0.490Fits in one request

GPT-5.2 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-5.2
SpecificationAnthropic Claude Sonnet 4.5OpenAI GPT-5.2
MakerAnthropicOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedSeptember 29, 2025December 10, 2025
Context window1M400K
Input $/Mtok$3.00$1.75
Output $/Mtok$15.00$14.00
Coding index39.555.9
Independent measurements behind it33
Cost per solved task$1.16$1.91
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Sonnet 4.5 better than GPT-5.2 for coding?

Pick GPT-5.2 for coding: it scores 55.9 on the Vibe Coding Index against 39.5 for Claude Sonnet 4.5. Pick Claude Sonnet 4.5 for a lower cost per solved task ($1.16 against $1.91) and a larger context window (1M against 400K tokens).

Which is cheaper, Claude Sonnet 4.5 or GPT-5.2?

Claude Sonnet 4.5 costs $3.00 per million input tokens and $15.00 per million output tokens; GPT-5.2 costs $1.75 and $14.00. Per solved SWE-bench Verified task, Claude Sonnet 4.5 costs $1.16 and GPT-5.2 $1.91.

Which has the bigger context window, Claude Sonnet 4.5 or GPT-5.2?

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

How many benchmarks is the Claude Sonnet 4.5 vs GPT-5.2 comparison based on?

89 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-5.2'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-5-2" title="Claude Sonnet 4.5 vs GPT-5.2, 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-5-2">LLMBenchmark.ai, Claude Sonnet 4.5 vs GPT-5.2</a></p>