Claude Opus 4.5 vs GPT-5.2

GPT-5.2 leads Claude Opus 4.5 on coding, 55.9 to 44.0 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; 102 benchmarks have a result for both.

Replace Claude Opus 4.5 Replace GPT-5.2

Claude Opus 4.5Anthropic

Coding: 44.0
Overall: 55.7
Output $/M: $25.00

GPT-5.2OpenAI

Coding: 55.9
Overall: 60.7
Output $/M: $14.00

vs boards won of 102 shared, 1 tied

Claude Opus 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 44.0 for Claude Opus 4.5.

Pick Claude Opus 4.5 for a lower cost per solved task ($1.37 against $1.91) and work measured by SWE-bench Verified or SWE-bench Multilingual, where it leads.

Model AClaude Opus 4.5Anthropic44.0/1003 independent benchmarks$1.37 per solved task Model BGPT-5.2OpenAI55.9/1003 independent benchmarks$1.91 per solved task

102612

Shared results: 102
Claude Opus 4.5 only: 6
GPT-5.2 only: 12
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.

Coding
Vibe Coding Index, six public coding benchmarks
GPT-5.2
GPT-5.2 scores 55.9 against 44.0.
3 benchmarks behind each score
Intelligence
AA Intelligence Index
GPT-5.2
GPT-5.2 leads, 30.4 against 29.1.
Same board, both measured
Reasoning
GPQA Diamond
GPT-5.2
GPT-5.2 leads, 91.7% against 85.9%.
Same board, both measured
Math
AIME
GPT-5.2
GPT-5.2 leads, 96.9% against 95.4%.
Same board, both measured
Knowledge
MMLU Pro
Claude Opus 4.5
Claude Opus 4.5 leads, 87.3% against 86.2%.
Same board, both measured
Web design
Design Arena: websites
Claude Opus 4.5
Claude Opus 4.5 leads, 1247 against 1195.
Same board, both measured
Long documents
Listed context window
GPT-5.2
GPT-5.2 takes 400K tokens against 200K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
GPT-5.2
Claude Opus 4.5 $0.018, GPT-5.2 $0.0088 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
Claude Opus 4.5
Claude Opus 4.5 $1.37, GPT-5.2 $1.91.
Published attempt cost and pass rate

At a glance

Coding index: Claude Opus 4.5 44.0 from 3 benchmarks, GPT-5.2 55.9 from 3 benchmarks.
Widest category: Math, 11.7 points apart on average over 10 shared benchmarks.
Widest single gap: VPCT: Claude Opus 4.5 40.0% against GPT-5.2 84.0%, 44.0 points apart on a 0 to 100 scale.
Output price: Claude Opus 4.5 $25.00 against GPT-5.2 $14.00 per million output tokens, 1.8x apart.
Context window: Claude Opus 4.5 takes 200K 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
Category	Claude Opus 4.5	GPT-5.2	Ties
Coding	7	6	1 tie
Intelligence	0	2
Agentic work	9	2
Reasoning	5	11
Math	4	6
Knowledge	10	5
Web design	8	0
General	21	5
All shared boards	64	37	1 tie

CodingLike-for-likeSix of these boards feed the Vibe Coding Index76

Coding benchmarks for Claude Opus 4.5 and GPT-5.2
Benchmark	Claude Opus 4.5	GPT-5.2	Leader
SWE-bench Verified	79.2%	72.8%	Claude Opus 4.5
SWE-bench (full test set)	52.6%	Not measured	Only Claude Opus 4.5 measured
SWE-bench Multilingual	70.7%	66.7%	Claude Opus 4.5
LMArena WebDev	1494	1417	Claude Opus 4.5
LiveCodeBench (Vals AI)	83.7%	85.4%	GPT-5.2
SWE-bench Verified (Vals AI)	76.4%	75.8%	Claude Opus 4.5
Vibe Code Bench (Vals AI)	20.6%	53.5%	GPT-5.2
LiveCodeBench (Artificial Analysis run)	87.1%	89.4%	GPT-5.2
Terminal-Bench Hard (Artificial Analysis run)	47.0%	47.0%	Tie
Terminal-Bench	63.1%	64.9%	GPT-5.2
GSO-Bench	26.5%	27.5%	GPT-5.2
WeirdML	63.7%	72.2%	GPT-5.2
Cybench	82.0%	Not measured	Only Claude Opus 4.5 measured
ALE-Bench	Not measured	1293.5	Only GPT-5.2 measured
LMArena Text: coding	1503	1442	Claude Opus 4.5
LMArena Text: software and IT	1483	1434	Claude Opus 4.5
LMArena WebDev: React	1478	Not measured	Only Claude Opus 4.5 measured
LMArena WebDev: HTML	1510	1427	Claude Opus 4.5
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 Opus 4.5 and GPT-5.2
Benchmark	Claude Opus 4.5	GPT-5.2	Leader
AA Intelligence Index	29.1	30.4	GPT-5.2
Epoch Capabilities Index	150.1	153.7	GPT-5.2

Agentic workLike-for-likePublic boards, shown as published, kept out of the index92

Agentic work benchmarks for Claude Opus 4.5 and GPT-5.2
Benchmark	Claude Opus 4.5	GPT-5.2	Leader
Design Arena: agents building web apps	1159	1086	Claude Opus 4.5
Design Arena: agents building full-stack apps	1156	1043	Claude Opus 4.5
Design Arena: agents building mobile apps	1189	1093	Claude Opus 4.5
Design Arena: agents building Android apps	1176	1059	Claude Opus 4.5
Design Arena: agents building Godot games	Not measured	1142	Only GPT-5.2 measured
τ²-Bench Telecom	89.5%	84.8%	Claude Opus 4.5
METR time horizons	75.0%	75.3%	GPT-5.2
Remote Labor Index	3.8%	2.5%	Claude Opus 4.5
GDPval	45.5%	49.7%	GPT-5.2
BALROG	43.5%	Not measured	Only Claude Opus 4.5 measured
DeepResearch Bench	54.8%	41.1%	Claude Opus 4.5
OSWorld	66.3%	Not measured	Only Claude Opus 4.5 measured
Vending-Bench 2	$4,967	$3,591	Claude Opus 4.5
Berkeley Function Calling Leaderboard (BFCL)	77.5%	55.9%	Claude Opus 4.5
Neither model has a result on the other 27 boards here

ReasoningLike-for-likePublic boards, shown as published, kept out of the index511

Reasoning benchmarks for Claude Opus 4.5 and GPT-5.2
Benchmark	Claude Opus 4.5	GPT-5.2	Leader
GPQA Diamond	85.9%	91.7%	GPT-5.2
MMMU Pro (Vals AI)	83.0%	86.7%	GPT-5.2
GPQA Diamond (Artificial Analysis run)	86.6%	90.3%	GPT-5.2
Humanity's Last Exam (Artificial Analysis run)	30.1%	37.7%	GPT-5.2
GPQA Diamond (Epoch AI run)	86.0%	91.4%	GPT-5.2
ARC-AGI	80.0%	86.2%	GPT-5.2
ARC-AGI-2	37.6%	52.9%	GPT-5.2
SimpleBench	62.0%	45.8%	Claude Opus 4.5
Chess puzzles	14.0%	48.0%	GPT-5.2
Mystery game puzzles	22.0%	23.0%	GPT-5.2
EBR-bench	14.3%	23.0%	GPT-5.2
VPCT	40.0%	84.0%	GPT-5.2
LMArena Text: hard prompts	1476	1428	Claude Opus 4.5
LMArena Text: expert	1487	1445	Claude Opus 4.5
LMArena Text: hard prompts in English	1482	1431	Claude Opus 4.5
LMArena Vision: diagrams	Not measured	1265	Only GPT-5.2 measured
LMArena Vision: homework	Not measured	1276	Only GPT-5.2 measured
Kagi LLM Benchmark	80.2%	73.3%	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 index46

Math benchmarks for Claude Opus 4.5 and GPT-5.2
Benchmark	Claude Opus 4.5	GPT-5.2	Leader
AIME	95.4%	96.9%	GPT-5.2
MGSM (Vals AI)	95.2%	94.0%	Claude Opus 4.5
AA Math Index	91.3	99.0	GPT-5.2
AIME 2025 (Artificial Analysis run)	91.3%	99.0%	GPT-5.2
OTIS Mock AIME	86.1%	96.1%	GPT-5.2
FrontierMath, tiers 1 to 3	34.4%	67.4%	GPT-5.2
FrontierMath, tier 4	4.9%	31.7%	GPT-5.2
ProofBench	36.0%	15.0%	Claude Opus 4.5
LMArena Text: math	1463	1440	Claude Opus 4.5
LMArena Text: mathematical work	1468	1442	Claude Opus 4.5
Neither model has a result on the other 3 boards here

KnowledgeLike-for-likePublic boards, shown as published, kept out of the index105

Knowledge benchmarks for Claude Opus 4.5 and GPT-5.2
Benchmark	Claude Opus 4.5	GPT-5.2	Leader
MMLU Pro	87.3%	86.2%	Claude Opus 4.5
LegalBench (Vals AI)	84.6%	82.8%	Claude Opus 4.5
CaseLaw (Vals AI)	62.6%	66.0%	GPT-5.2
CorpFin (Vals AI)	65.1%	65.9%	GPT-5.2
TaxEval (Vals AI)	74.9%	75.8%	GPT-5.2
MortgageTax (Vals AI)	68.7%	67.1%	Claude Opus 4.5
MedQA (Vals AI)	95.9%	94.1%	Claude Opus 4.5
MedCode (Vals AI)	49.2%	49.8%	GPT-5.2
MMLU Pro (Artificial Analysis run)	89.5%	87.4%	Claude Opus 4.5
SimpleQA Verified	45.7%	37.1%	Claude Opus 4.5
GeoBench	75.0%	Not measured	Only Claude Opus 4.5 measured
LMArena Text: science	1454	1425	Claude Opus 4.5
LMArena Text: medicine and healthcare	1444	1425	Claude Opus 4.5
LMArena Text: legal and government	1459	1427	Claude Opus 4.5
LMArena Text: business and finance	1448	1414	Claude Opus 4.5
FACTS Benchmark Suite	43.9%	48.5%	GPT-5.2
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 4.5 and GPT-5.2
Benchmark	Claude Opus 4.5	GPT-5.2	Leader
Design Arena: websites	1247	1195	Claude Opus 4.5
Design Arena: UI components	1235	1190	Claude Opus 4.5
Design Arena: game dev	1228	1195	Claude Opus 4.5
Design Arena: data viz	1243	1202	Claude Opus 4.5
Design Arena: 3D	1213	1079	Claude Opus 4.5
Design Arena: all code categories	1242	1170	Claude Opus 4.5
Design Arena: SVG	1180	1139	Claude Opus 4.5
Design Arena: ASCII art	1190	1152	Claude 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 index215

General benchmarks for Claude Opus 4.5 and GPT-5.2
Benchmark	Claude Opus 4.5	GPT-5.2	Leader
SAGE (Vals AI)	52.1%	49.3%	Claude Opus 4.5
MedScribe (Vals AI)	85.3%	84.4%	Claude Opus 4.5
IFBench	58.0%	75.4%	GPT-5.2
Long context reasoning (AA-LCR)	77.3%	82.7%	GPT-5.2
DTBench	89.9%	90.9%	GPT-5.2
LMCA	44.5%	43.9%	Claude Opus 4.5
CL-bench	21.1%	18.2%	Claude Opus 4.5
Furniture assembly	28.3%	38.3%	GPT-5.2
LMArena Text	1451	1416	Claude Opus 4.5
LMArena Text: instruction following	1478	1409	Claude Opus 4.5
LMArena Text: creative writing	1445	1376	Claude Opus 4.5
LMArena Vision	Not measured	1246	Only GPT-5.2 measured
LMArena Text: English	1461	1422	Claude Opus 4.5
LMArena Text: non-English	1438	1405	Claude Opus 4.5
LMArena Text: Chinese	1470	1447	Claude Opus 4.5
LMArena Text: German	1449	1444	Claude Opus 4.5
LMArena Text: Japanese	1417	1420	GPT-5.2
LMArena Text: Korean	1424	1374	Claude Opus 4.5
LMArena Text: French	1471	1454	Claude Opus 4.5
LMArena Text: Spanish	1457	1413	Claude Opus 4.5
LMArena Text: Russian	1447	1415	Claude Opus 4.5
LMArena Text: Polish	1439	1426	Claude Opus 4.5
LMArena Text: multi-turn	1466	1419	Claude Opus 4.5
LMArena Text: longer queries	1479	1413	Claude Opus 4.5
LMArena Text: writing and language	1452	1392	Claude Opus 4.5
LMArena Text: entertainment and media	1434	1378	Claude Opus 4.5
LMArena Vision: English	Not measured	1243	Only GPT-5.2 measured
LMArena Vision: Chinese	Not measured	1305	Only GPT-5.2 measured
LMArena Vision: reading text	Not measured	1257	Only GPT-5.2 measured
LMArena Vision: humor	Not measured	1227	Only GPT-5.2 measured
LMArena Vision: captioning	Not measured	1267	Only GPT-5.2 measured
LMArena Vision: recognizing things	Not measured	1232	Only GPT-5.2 measured
LMArena Vision: creative writing	Not measured	1225	Only GPT-5.2 measured
LMArena Document	1462	1405	Claude Opus 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 Opus 4.5 and GPT-5.2
Benchmark	Claude Opus 4.5	GPT-5.2	Leader
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-5.2$0.0088Fits in one request

GPT-5.2 costs less

Repository review

50K input + 3K output tokens

Claude Opus 4.5$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 4.5$1.25Exceeds the context window

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 4.5 and GPT-5.2
Specification	Anthropic Claude Opus 4.5	OpenAI GPT-5.2
Maker	Anthropic	OpenAI
Weights	No public weights listed	No public weights listed
Released	November 24, 2025	December 10, 2025
Context window	200K	400K
Input $/Mtok	$5.00	$1.75
Output $/Mtok	$25.00	$14.00
Coding index	44.0	55.9
Independent measurements behind it	3	3
Cost per solved task	$1.37	$1.91
Source	OpenRouter listing	OpenRouter listing

Questions

Is Claude Opus 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 44.0 for Claude Opus 4.5. Pick Claude Opus 4.5 for a lower cost per solved task ($1.37 against $1.91) and work measured by SWE-bench Verified or SWE-bench Multilingual, where it leads.

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

Claude Opus 4.5 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 4.5 costs $1.37 and GPT-5.2 $1.91.

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

GPT-5.2, with 400K tokens against 200K.

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

102 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-5.2'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-4-5-vs-gpt-5-2" title="Claude Opus 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-opus-4-5-vs-gpt-5-2">LLMBenchmark.ai, Claude Opus 4.5 vs GPT-5.2</a></p>

Claude Opus 4.5 or GPT-5.2: which to pick

Which one for your work

Coding

Intelligence

Reasoning

Math

Knowledge

Web design

Long documents

Everyday cost

Cost per solved task

At a glance

Benchmark by benchmark

What each workload costs

Chat turn

Repository review

Agent loop

Specification differences

Questions

Compare next