Enter opens the highlighted result. Esc closes.

Claude Opus 4.6 vs GPT-5.2

Claude Opus 4.6 leads GPT-5.2 on coding, 57.2 to 55.9 on the Vibe Coding Index, and GPT-5.2 costs 1.8x less per output token ($14.00 vs $25.00 per million). Updated October 22, 2026; 103 benchmarks have a result for both.

Replace Claude Opus 4.6 Replace GPT-5.2
Claude Opus 4.6Anthropic
Coding
57.2
Overall
66.0
Output $/M
$25.00
86
GPT-5.2OpenAI
Coding
55.9
Overall
60.7
Output $/M
$14.00
17
vs boards won of 103 shared

Claude Opus 4.6 or GPT-5.2: which to pick

Claude Opus 4.6 and GPT-5.2 are level for coding, 57.2 against 55.9 on the Vibe Coding Index, so price and context decide.

Pick GPT-5.2 for output tokens 1.8x cheaper ($14.00 vs $25.00 per million) and work measured by LiveCodeBench (Vals AI) or GPQA Diamond, where it leads. Pick Claude Opus 4.6 for a lower cost per solved task ($1.56 against $1.91) and a larger context window (1M against 400K tokens).

Model AClaude Opus 4.6Anthropic57.2/1004 independent benchmarks$1.56 per solved taskModel BGPT-5.2OpenAI55.9/1003 independent benchmarks$1.91 per solved task
Shared results
103
Claude Opus 4.6 only
7
GPT-5.2 only
11
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 4.6 57.2 from 4 benchmarks, GPT-5.2 55.9 from 3 benchmarks.
Widest category
Agentic work, 13.7 points apart on average over 9 shared benchmarks.
Widest single gap
ProofBench: Claude Opus 4.6 50.0% against GPT-5.2 15.0%, 35.0 points apart on a 0 to 100 scale.
Output price
Claude Opus 4.6 $25.00 against GPT-5.2 $14.00 per million output tokens, 1.8x apart.
Context window
Claude Opus 4.6 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 Opus 4.6BarsGPT-5.2Ties
Coding121
Intelligence20
Agentic work90
Reasoning116
Math34
Knowledge113
Web design80
General303
All shared boards8617
CodingLike-for-likeSix of these boards feed the Vibe Coding Index121
Coding benchmarks for Claude Opus 4.6 and GPT-5.2
BenchmarkClaude Opus 4.6GPT-5.2Leader
SWE-bench Verified75.6%72.8%Claude Opus 4.6
SWE-bench Multilingual72.0%66.7%Claude Opus 4.6
LMArena WebDev15471417Claude Opus 4.6
LiveCodeBench (Vals AI)84.7%85.4%GPT-5.2
SWE-bench Verified (Vals AI)78.2%75.8%Claude Opus 4.6
Vibe Code Bench (Vals AI)57.6%53.5%Claude Opus 4.6
LiveCodeBench (Artificial Analysis run)Not measured89.4%Only GPT-5.2 measured
Terminal-Bench Hard (Artificial Analysis run)48.5%47.0%Claude Opus 4.6
Terminal-Bench79.8%64.9%Claude Opus 4.6
FrontierCode26.6%Not measuredOnly Claude Opus 4.6 measured
GSO-Bench41.2%27.5%Claude Opus 4.6
WeirdML78.0%72.2%Claude Opus 4.6
Cybench93.0%Not measuredOnly Claude Opus 4.6 measured
ALE-BenchNot measured1293.5Only GPT-5.2 measured
LMArena Text: coding15341442Claude Opus 4.6
LMArena Text: software and IT15271434Claude Opus 4.6
LMArena WebDev: React1539Not measuredOnly Claude Opus 4.6 measured
LMArena WebDev: HTML15591427Claude Opus 4.6
LMArena WebDev: from an image1543Not measuredOnly Claude Opus 4.6 measured
Neither model has a result on the other 20 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Claude Opus 4.6 and GPT-5.2
BenchmarkClaude Opus 4.6GPT-5.2Leader
AA Intelligence Index31.930.4Claude Opus 4.6
Epoch Capabilities Index155.7153.7Claude Opus 4.6
Agentic workLike-for-likePublic boards, shown as published, kept out of the index90
Agentic work benchmarks for Claude Opus 4.6 and GPT-5.2
BenchmarkClaude Opus 4.6GPT-5.2Leader
Design Arena: agents building web apps12061086Claude Opus 4.6
Design Arena: agents building full-stack apps12201043Claude Opus 4.6
Design Arena: agents building mobile apps12071093Claude Opus 4.6
Design Arena: agents building Android apps11971059Claude Opus 4.6
Design Arena: agents building Godot gamesNot measured1142Only GPT-5.2 measured
Design Arena: agents building games1212Not measuredOnly Claude Opus 4.6 measured
τ²-Bench Telecom92.1%84.8%Claude Opus 4.6
APEX-Agents46.3%Not measuredOnly Claude Opus 4.6 measured
METR time horizons78.9%75.3%Claude Opus 4.6
Remote Labor Index4.2%2.5%Claude Opus 4.6
GDPvalNot measured49.7%Only GPT-5.2 measured
DeepResearch Bench55.3%41.1%Claude Opus 4.6
Vending-Bench 2$8,018$3,591Claude Opus 4.6
Berkeley Function Calling Leaderboard (BFCL)Not measured55.9%Only GPT-5.2 measured
Neither model has a result on the other 27 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index116
Reasoning benchmarks for Claude Opus 4.6 and GPT-5.2
BenchmarkClaude Opus 4.6GPT-5.2Leader
GPQA Diamond89.7%91.7%GPT-5.2
MMMU Pro (Vals AI)83.9%86.7%GPT-5.2
GPQA Diamond (Artificial Analysis run)89.6%90.3%GPT-5.2
Humanity's Last Exam (Artificial Analysis run)39.9%37.7%Claude Opus 4.6
GPQA Diamond (Epoch AI run)90.5%91.4%GPT-5.2
ARC-AGI94.0%86.2%Claude Opus 4.6
ARC-AGI-269.2%52.9%Claude Opus 4.6
SimpleBench67.6%45.8%Claude Opus 4.6
Chess puzzles21.0%48.0%GPT-5.2
Mystery game puzzles25.0%23.0%Claude Opus 4.6
EBR-bench12.7%23.0%GPT-5.2
VPCTNot measured84.0%Only GPT-5.2 measured
LMArena Text: hard prompts15251428Claude Opus 4.6
LMArena Text: expert15441445Claude Opus 4.6
LMArena Text: hard prompts in English15301431Claude Opus 4.6
LMArena Vision: diagrams13401265Claude Opus 4.6
LMArena Vision: homework13371276Claude Opus 4.6
Kagi LLM Benchmark83.6%73.3%Claude Opus 4.6
Neither model has a result on the other 4 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index34
Math benchmarks for Claude Opus 4.6 and GPT-5.2
BenchmarkClaude Opus 4.6GPT-5.2Leader
AIME95.6%96.9%GPT-5.2
MGSM (Vals AI)Not measured94.0%Only GPT-5.2 measured
AA Math IndexNot measured99.0Only GPT-5.2 measured
AIME 2025 (Artificial Analysis run)Not measured99.0%Only GPT-5.2 measured
OTIS Mock AIME94.4%96.1%GPT-5.2
FrontierMath, tiers 1 to 366.0%67.4%GPT-5.2
FrontierMath, tier 426.8%31.7%GPT-5.2
ProofBench50.0%15.0%Claude Opus 4.6
LMArena Text: math15181440Claude Opus 4.6
LMArena Text: mathematical work15251442Claude Opus 4.6
Neither model has a result on the other 3 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index113
Knowledge benchmarks for Claude Opus 4.6 and GPT-5.2
BenchmarkClaude Opus 4.6GPT-5.2Leader
MMLU Pro89.1%86.2%Claude Opus 4.6
LegalBench (Vals AI)85.3%82.8%Claude Opus 4.6
CaseLaw (Vals AI)62.1%66.0%GPT-5.2
CorpFin (Vals AI)67.0%65.9%Claude Opus 4.6
TaxEval (Vals AI)76.0%75.8%Claude Opus 4.6
MortgageTax (Vals AI)68.5%67.1%Claude Opus 4.6
MedQA (Vals AI)95.4%94.1%Claude Opus 4.6
MedCode (Vals AI)49.1%49.8%GPT-5.2
MMLU Pro (Artificial Analysis run)Not measured87.4%Only GPT-5.2 measured
SimpleQA Verified47.0%37.1%Claude Opus 4.6
LMArena Text: science15191425Claude Opus 4.6
LMArena Text: medicine and healthcare15041425Claude Opus 4.6
LMArena Text: legal and government15121427Claude Opus 4.6
LMArena Text: business and finance14971414Claude Opus 4.6
FACTS Benchmark Suite41.5%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 index80
Web design benchmarks for Claude Opus 4.6 and GPT-5.2
BenchmarkClaude Opus 4.6GPT-5.2Leader
Design Arena: websites12911195Claude Opus 4.6
Design Arena: UI components12811190Claude Opus 4.6
Design Arena: game dev12771195Claude Opus 4.6
Design Arena: data viz12791202Claude Opus 4.6
Design Arena: 3D12731079Claude Opus 4.6
Design Arena: all code categories12881170Claude Opus 4.6
Design Arena: SVG12271139Claude Opus 4.6
Design Arena: ASCII art12551152Claude Opus 4.6
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index303
General benchmarks for Claude Opus 4.6 and GPT-5.2
BenchmarkClaude Opus 4.6GPT-5.2Leader
SAGE (Vals AI)51.6%49.3%Claude Opus 4.6
MedScribe (Vals AI)86.7%84.4%Claude Opus 4.6
IFBench53.1%75.4%GPT-5.2
Long context reasoning (AA-LCR)78.0%82.7%GPT-5.2
DTBench91.2%90.9%Claude Opus 4.6
LMCA55.8%43.9%Claude Opus 4.6
CL-bench20.7%18.2%Claude Opus 4.6
Furniture assembly28.3%38.3%GPT-5.2
CL-bench Life17.0%Not measuredOnly Claude Opus 4.6 measured
LMArena Text15011416Claude Opus 4.6
LMArena Text: instruction following15211409Claude Opus 4.6
LMArena Text: creative writing15051376Claude Opus 4.6
LMArena Vision13161246Claude Opus 4.6
LMArena Text: English15111422Claude Opus 4.6
LMArena Text: non-English14881405Claude Opus 4.6
LMArena Text: Chinese15511447Claude Opus 4.6
LMArena Text: German15001444Claude Opus 4.6
LMArena Text: Japanese14881420Claude Opus 4.6
LMArena Text: Korean14641374Claude Opus 4.6
LMArena Text: French15121454Claude Opus 4.6
LMArena Text: Spanish15101413Claude Opus 4.6
LMArena Text: Russian14971415Claude Opus 4.6
LMArena Text: Polish14991426Claude Opus 4.6
LMArena Text: multi-turn15111419Claude Opus 4.6
LMArena Text: longer queries15181413Claude Opus 4.6
LMArena Text: writing and language15021392Claude Opus 4.6
LMArena Text: entertainment and media14921378Claude Opus 4.6
LMArena Vision: English13241243Claude Opus 4.6
LMArena Vision: Chinese13701305Claude Opus 4.6
LMArena Vision: reading text13261257Claude Opus 4.6
LMArena Vision: humor13141227Claude Opus 4.6
LMArena Vision: captioningNot measured1267Only GPT-5.2 measured
LMArena Vision: recognizing things12741232Claude Opus 4.6
LMArena Vision: creative writing13311225Claude Opus 4.6
LMArena Document15071405Claude Opus 4.6
Neither model has a result on the other 11 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Claude Opus 4.6 and GPT-5.2
BenchmarkClaude Opus 4.6GPT-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 Opus 4.6$0.018Fits in one request
GPT-5.2$0.0088Fits in one request

GPT-5.2 costs less

Repository review

50K input + 3K output tokens

Claude Opus 4.6$0.325Fits in one request
GPT-5.2$0.130Fits in one request

GPT-5.2 costs less

Agent loop

200K input + 10K output tokens

Claude Opus 4.6$1.25Fits 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 Opus 4.6 and GPT-5.2
SpecificationAnthropic Claude Opus 4.6OpenAI GPT-5.2
MakerAnthropicOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedFebruary 4, 2026December 10, 2025
Context window1M400K
Input $/Mtok$5.00$1.75
Output $/Mtok$25.00$14.00
Coding index57.255.9
Independent measurements behind it43
Cost per solved task$1.56$1.91
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Opus 4.6 better than GPT-5.2 for coding?

Claude Opus 4.6 and GPT-5.2 are level for coding, 57.2 against 55.9 on the Vibe Coding Index, so price and context decide. Pick GPT-5.2 for output tokens 1.8x cheaper ($14.00 vs $25.00 per million) and work measured by LiveCodeBench (Vals AI) or GPQA Diamond, where it leads. Pick Claude Opus 4.6 for a lower cost per solved task ($1.56 against $1.91) and a larger context window (1M against 400K tokens).

Which is cheaper, Claude Opus 4.6 or GPT-5.2?

Claude Opus 4.6 costs $5.00 per million input tokens and $25.00 per million output tokens; GPT-5.2 costs $1.75 and $14.00. Per solved SWE-bench Verified task, Claude Opus 4.6 costs $1.56 and GPT-5.2 $1.91.

Which has the bigger context window, Claude Opus 4.6 or GPT-5.2?

Claude Opus 4.6, with 1M tokens against 400K.

How many benchmarks is the Claude Opus 4.6 vs GPT-5.2 comparison based on?

103 benchmarks have a result for both models as of October 22, 2026. Claude Opus 4.6's coding index rests on 4 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-opus-4-6-vs-gpt-5-2" title="Claude Opus 4.6 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-opus-4-6-vs-gpt-5-2">LLMBenchmark.ai, Claude Opus 4.6 vs GPT-5.2</a></p>