BenchLeader
Menu
Best LLMsChoose a modelLeaderboardsModelsBenchmarksProvidersReleases9

Claude Opus 5 vs GPT-5.2

Full profiles: Claude Opus 5 (Anthropic) and GPT-5.2 (OpenAI): every benchmark, price and rank.

Updated · Data from 11 sources

As of 26 Oct 2026, Claude Opus 5 (max) leads on quality (68.8 vs 60.7 on the BenchLeader Index), but GPT-5.2 (xhigh) costs 2.1× less, so it is the better buy unless you need the extra quality. Pick Claude Opus 5 for knowledge (72 vs 57); pick GPT-5.2 for long context (66 vs 65).

Claude Opus 5 benchmarks max Anthropic GPT-5.2 benchmarks xhigh OpenAIOpen in the comparison tool

Which to pick for…

The pick's numbers come first. Category scores on the BenchLeader scale (50 is the average model, 15 points one standard deviation). High confidence means a lead of half a standard deviation or more; under one point is called either.

Use casePickWhyConfidence
CodingClaude Opus 570 vs 63 category score; WeirdML 91.8% vs 72.2%Medium
Agents & tool useClaude Opus 564 vs 55 category scoreHigh
MathsClaude Opus 571 vs 57 category score; FrontierMath Tiers 1–3 85.6% vs 67.4%High
ReasoningClaude Opus 574 vs 61 category score; GPQA Diamond 93.9% vs 91.4%High
KnowledgeClaude Opus 572 vs 57 category score; SimpleQA Verified 59.9% vs 37.1%High
Long documentsGPT-5.266 vs 65 category score; AA-LCR 82.7% vs 79.3%Medium
Chat quality (human preference)–Only Claude Opus 5 has an Arena rating (69 category score)Not comparable
Lowest costGPT-5.2$4.81 vs $10.00 per 1M blended; agentic coding session $0.161 vs $0.400–
Fastest first answerClaude Opus 568.7 s (Claude Opus 5 (max)) vs 124.7 s (GPT-5.2 (xhigh)) to the first answer token–
High volume on a budgetNeither flagshipA smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs–

Key differences

  • Claude Opus 5 (max) leads on quality: 68.8 vs 60.7.
  • Claude Opus 5 (max) is stronger in agents & tools, coding, composite, human preference, knowledge, maths, multimodal, reasoning.
  • GPT-5.2 (xhigh) is stronger in long context, instruction following.
  • GPT-5.2 (xhigh) is 2.1× cheaper ($4.81 vs $10.00 per 1M blended).
  • GPT-5.2 (xhigh) streams 1.6× faster (81 vs 51 tokens per second).

At a glance

SpecClaude Opus 5GPT-5.2
DeveloperAnthropicOpenAI
Released24 Jul 202611 Dec 2025
Context window (tokens)1,000,000400,000
Compared atClaude Opus 5 (max)GPT-5.2 (xhigh)
Open weightsNoNo
Price in / out / cached input per 1M$5.00 / $25.00 / $0.500$1.75 / $14.00 / $0.175

Category by category

Category scores on the BenchLeader scale: 50 is the average evaluated model, 15 points is one standard deviation. A gap under one point is called level.

CategoryClaude Opus 5 (max)GPT-5.2 (xhigh)Leader
Reasoning74.160.7Claude Opus 5
Coding70.262.9Claude Opus 5
Agents & tools64.354.9Claude Opus 5
Maths70.656.8Claude Opus 5
Knowledge71.657.1Claude Opus 5
Instruction following–73.6not comparable
Human preference68.5–not comparable
Multimodal67.9–not comparable
Long context64.766.4GPT-5.2
Composite86.363.5Claude Opus 5

Where sources disagree

Across the 22 benchmarks both have, Claude Opus 5 leads 20, GPT-5.2 leads 2. Every overall index that rates both puts Claude Opus 5 ahead.

Overall indexClaude Opus 5 (max)GPT-5.2 (xhigh)Leader
BenchLeader Index68.860.7Claude Opus 5
AA Intelligence Index v4.3.250.830.4Claude Opus 5
Arena Text14911437†Claude Opus 5

Each publisher runs its own tasks, harnesses and effort settings, so their overall verdicts can differ; BenchLeader reconciles them on one scale. † measured at another effort setting of the same model (the publisher did not test the one compared here).

Price, speed and latency

List prices blended at three input tokens per output token. Per-task prices use the token counts on the methodology page; suite cost is what Artificial Analysis paid to run its whole Intelligence Index.

MeasureClaude Opus 5 (max)GPT-5.2 (xhigh)
Blended price per 1M tokens$10.00$4.81
Input / output per 1M$5.00 / $25.00$1.75 / $14.00
Cached input per 1M$0.500$0.175
Price per task: chat reply$0.0095$0.0049
Price per task: summarize a 30-page report$0.075$0.029
Price per task: code edit$0.068$0.032
Price per task: agentic coding session$0.400$0.161
Price per task: structured extraction$0.015$0.0063
Cost to run a full benchmark suite$5.86–
Output speed51 tok/s81 tok/s
Time to first answer68.7 s124.7 s
Time to a complete answer78.4 s130.9 s

Each model is compared at its best-ranked reasoning-effort setting. Claude Opus 5 (max) scores 68.8 and takes 69 s to its first answer token; Claude Opus 5 (high) scores 67.9 in 17 s, Claude Opus 5 (xhigh) scores 67.4 in 31 s. GPT-5.2 (xhigh) scores 60.7 and takes 125 s to its first answer token; GPT-5.2 scores 58.0 in 2 s, GPT-5.2 (medium) scores 57.6 in 2 s. Higher effort means more thinking before the answer: better scores, longer waits and more tokens billed. How reasoning effort changes scores and cost.

Every benchmark

157 benchmarks, grouped by category; each name links to the board and its leaders. † measured at another effort setting of the same model, shown for reference and not counted as a win.

MetricPublisherClaude Opus 5 (max)GPT-5.2 (xhigh)
BenchLeader IndexBenchLeader68.860.7
Agents & tools scoreBenchLeader64.354.9
Coding scoreBenchLeader70.262.9
Composite scoreBenchLeader86.363.5
Human preference scoreBenchLeader68.5–
Knowledge scoreBenchLeader71.657.1
Long context scoreBenchLeader64.766.4
Maths scoreBenchLeader70.656.8
Multimodal scoreBenchLeader67.9–
Reasoning scoreBenchLeader74.160.7
Instruction following scoreBenchLeader–73.6
Blended price $/MBenchLeader$10.00$4.81
Output speedBenchLeader51 tok/s81 tok/s
Time to first answerBenchLeader68.7 s124.7 s
Context windowBenchLeader1,000,000 tokens400,000 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub93.9%91.4%
Humanity's Last ExamScale AI / CAIS–27.8%†
SimpleBenchSimpleBench80.6%†45.8%†
Arena Hard PromptsArena (LMArena)15151497†
LiveBench 1.0 ReasoningLiveBench91.2%83.2%†
GPQA Diamond (AA)Artificial Analysis93.2%90.3%
Humanity's Last Exam (AA)Artificial Analysis54.9%37.7%
GPQA Diamond (Vals)Vals AI93.4%†91.7%
Kagi LLM BenchmarkKagi LLM Benchmark–73.3%†
ARC-AGI-1ARC Prize97.5%86.2%
ARC-AGI-2ARC Prize90.4%52.9%
ARC-AGI-3ARC Prize30.2%†–
CritPtArtificial Analysis29.1%11.6%
MysteryMechanismVals AI37.4%†–
SciPredictScale AI SEAL–20.6%†
Chess PuzzlesEpoch AI Benchmarking Hub43.0%48.0%
Mystery Game PuzzlesEpoch AI Benchmarking Hub59.0%22.0%†
CL-benchEpoch AI Benchmarking Hub–18.2%†
LMCAEpoch AI Benchmarking Hub63.3%43.9%
DTBenchEpoch AI Benchmarking Hub97.6%90.9%
ForecastBenchForecastBench66.5%64.2%†
BTF-3Epoch AI Benchmarking Hub12.0%†–
Coding
SWE-bench Verified (Epoch)Epoch AI Benchmarking Hub–73.8%†
SciCodeSciCode56.4%–
WeirdMLWeirdML91.8%72.2%
Show all 157 benchmarks
MetricPublisherClaude Opus 5 (max)GPT-5.2 (xhigh)
Coding
FrontierCodeCognition53.4%–
GSO-BenchGSO-Bench–27.4%†
Arena CodingArena (LMArena)15281515†
Arena WebDevArena (LMArena)16911417†
LiveBench 1.0 CodingLiveBench81.5%76.1%†
LiveCodeBenchVals AI89.0%†85.4%
IOIVals AI84.3%†–
SWE-bench (Vals)Vals AI97.0%†75.8%
SWE-Bench ProScale AI SEAL–29.9%†
SWE-bench Verified (bash only)SWE-bench–69.0%†
SWE-bench Verified (any scaffold)SWE-bench–72.8%†
Code MigrationVals AI57.5%†–
ProgramBenchVals AI3.0%†–
Vibe Code Bench 1-100Vals AI28.5%†–
Vibe Code Bench v1.1Vals AI88.4%†53.5%
SWE-Bench Pro (private)Scale AI SEAL–29.9%†
SWE Atlas: Codebase QnAScale AI SEAL63.2%†–
SWE Atlas: Test WritingScale AI SEAL62.2%†–
DeepSWE v1.1Epoch AI Benchmarking Hub73.7%–
CursorBenchCursor46.6%–
ALE-BenchEpoch AI Benchmarking Hub2164.6†1249.8†
AlgoTuneAlgoTune–2.0†
FrontierSWEEpoch AI Benchmarking Hub52.0%–
Terminal-Bench 4.0 (AA)Artificial Analysis49.0%–
Terminal-Bench 2.1 (AA)Artificial Analysis89.1%–
Startrise FrontendStartrise82.3%†–
Agents & tools
Terminal-BenchTerminal-Bench51.8%64.9%†
OSWorld-Verified 2.0OSWorld31.4%–
GDPvalOpenAI–49.7%†
Remote Labor IndexScale AI / CAIS–2.1%†
APEX-AgentsMercor65.8%–
Arena AgentArena (LMArena)8.2–
LiveBench Agentic CodingLiveBench65.2%50.3%†
Terminal-Bench HardArtificial Analysis–47.0%
τ²-Bench Telecom (AA)Artificial Analysis–84.8%
Terminal-Bench 2.1 (Vals)Vals AI84.6%†–
MCP AtlasScale AI SEAL85.8%†67.6%
HiL-BenchScale AI SEAL57.0%†–
BFCL OverallBerkeley Function Calling Leaderboard–55.9%†
τ²-benchτ²-bench–84.8%†
τ³-bench Bankingτ²-bench48.7%32.2%†
τ³-Banking (AA)Artificial Analysis42.1%11.1%†
Analyst Agent (AA)Artificial Analysis53.8%–
CUA-benchVals AI9.0%–
CyberBenchVals AI65.4%†–
Finance Agent v2Vals AI58.6%†–
Harvey's Legal Agent Benchmark v1Vals AI6.7%†–
Legal Research BenchVals AI55.3%†–
Poker AgentVals AI–1131.8%†
SkillsBenchVals AI60.4%†–
SREBenchVals AI12.2%†–
Tax Agent BenchVals AI45.5%†–
Terminal-Bench 2.0 (Vals)Vals AI–51.7%†
Terminal-Bench 4.0 (Vals)Vals AI53.5%†–
Terminal-Bench ScienceVals AI27.1%†–
Time Horizon Index: KSPVals AI18.8%†–
Arena SearchArena (LMArena)1214†–
BALROGBALROG63.4%–
DeepResearch BenchDeepResearch Bench–41.1%†
PostTrainBenchEpoch AI Benchmarking Hub35.0%†–
METR Time HorizonsMETR–75.3%†
GBAEvalEpoch AI Benchmarking Hub79.6%†–
Vending-Bench 2Andon Labs11181.9†3591.3†
AutomationBenchArtificial Analysis56.6%–
GDP.pdf (AA)Artificial Analysis21.6%–
EnterpriseOps-GymArtificial Analysis47.5%–
AA-Briefcase v1.1Artificial Analysis1657–
Terminal-Bench-Science 0.1 (AA)Artificial Analysis28.6%–
DeepSec-Bench (AA)Artificial Analysis25.9%–
FACTS SearchGoogle85.3%†–
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub85.6%67.4%
FrontierMath Tier 4Epoch AI Benchmarking Hub73.2%31.7%
OTIS Mock AIMEEpoch AI Benchmarking Hub98.9%96.1%
ProofBenchVals AI99.0%15.0%
LiveBench MathematicsLiveBench95.7%93.2%†
AIME (Vals)Vals AI–96.9%
MGSMVals AI–94.0%
AIME 2026MathArena–98.3%†
HMMT February 2026MathArena–97.0%†
MathArena ApexMathArena–13.5%†
Arena MathsArena (LMArena)15171454†
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub59.9%37.1%
LiveBench 1.0 Data AnalysisLiveBench74.5%78.2%†
AA-OmniscienceArtificial Analysis37.1-0.9
MMLU-ProVals AI91.6%†86.2%
LegalBenchVals AI87.0%†82.8%
CorpFinVals AI73.2%†65.9%
TaxEvalVals AI75.1%†75.8%
MedQAVals AI–94.1%
MultiNRCScale AI SEAL–42.2%†
BioMysteryBenchVals AI79.3%†–
CaseLaw v2Vals AI–66.0%
Excel Modeling BenchmarkVals AI73.6%†–
MedCodeVals AI63.6%†49.8%
MedScribeVals AI91.0%†84.4%
Public Benefits Bench v1.1Vals AI76.9%†–
DrugDiscoveryBenchScale AI SEAL53.7%29.3%
EBR-benchEpoch AI Benchmarking Hub45.7%23.0%
GDP.pdfEpoch AI Benchmarking Hub24.0%–
AA-Omniscience: accuracyArtificial Analysis60.9%44.3%
AA-Omniscience: non-hallucinationArtificial Analysis39.2%18.8%
Global-MMLU-Lite (AA)Artificial Analysis–89.8%†
Instruction following
LiveBench LanguageLiveBench88.7%79.8%†
LiveBench Instruction FollowingLiveBench63.8%61.8%†
IFBenchArtificial Analysis–75.4%
TutorBenchScale AI SEAL–53.5%†
Arena Instruction FollowingArena (LMArena)14951457†
Human preference
Arena TextArena (LMArena)14911476†
EQ-Bench 4EQ-Bench1360†–
Arena Creative WritingArena (LMArena)14741433†
Arena Multi-turnArena (LMArena)14871495†
Arena Longer QueriesArena (LMArena)15031472†
Multimodal
Arena VisionArena (LMArena)1320†1268†
MMMU-ProArtificial Analysis84.7%74.6%†
VISTAScale AI SEAL–46.6%†
MMMU-Pro (Vals)Vals AI89.9%†86.7%
MortgageTaxVals AI72.1%†67.1%
SAGEVals AI49.4%†49.3%
VPCTEpoch AI Benchmarking Hub–84.0%
Blueprint-Bench 2Epoch AI Benchmarking Hub30.4%†–
Long context
AA-LCRArtificial Analysis79.3%82.7%
Arena DocumentArena (LMArena)1490†1425†
MLCRArtificial Analysis11.1%–
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub163.9†153.7†
LiveBench 1.0LiveBench80.1%74.6%†
AA Intelligence Index v4.3.2Artificial Analysis50.830.4
Vals RSI IndexVals AI33.0%15.8%
Vals Science IndexVals AI47.9%†–
Vals Multimodal IndexVals AI73.9%†–
Safety & honesty
FORTRESSScale AI SEAL16.8%†17.5%†
MASKScale AI SEAL–86.7%†
PropensityBenchScale AI SEAL–34.4%†

Data as of 2026-10-26. Best configuration of each model; every score links to its source on the model pages.

What changed

  • Claude Opus 5 (max): 1 new result (Vals RSI Index).
  • GPT-5.2 (xhigh): 1 new result (Vals RSI Index).
  • Claude Opus 5 (max): 1 score revision.
  • Claude Opus 5 (max): 1 new result (ForecastBench); 1 score revision.
  • Claude Opus 5 (max): BenchLeader Index 68.3 → 68.9.
  • Claude Opus 5 (max): 4 new results (GDPval-AA v2.1, AA-Omniscience: accuracy, AA-Omniscience: non-hallucination…).
  • Claude Opus 5 (max): 1 score revision.
  • Claude Opus 5 (max): 2 score revisions.
  • GPT-5.2 (xhigh): 1 score revision.
  • Claude Opus 5 (max): 2 new results (Terminal-Bench-Science 0.1 (AA), DeepSec-Bench (AA)).

Rankings: Best LLM overall · Best LLM for coding · Best LLM for agents · Best cheap LLMs

Claude Opus 5 vs GPT-5.2: questions

Is Claude Opus 5 better than GPT-5.2?
Claude Opus 5 (max) leads on quality: 68.8 vs 60.7. The BenchLeader Index combines every independent quality benchmark; Claude Opus 5 (max) is ahead overall as of 2026-10-26, but check the category scores for your use.
Which is cheaper, Claude Opus 5 or GPT-5.2, and will that change?
GPT-5.2 is cheaper today: $4.81 against $10.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Is Claude Opus 5 better than GPT-5.2 for coding?
Claude Opus 5 scores higher in coding (70 vs 63 on the category index, where 50 is average). On WeirdML, the top shared coding benchmark, it is 91.8% for Claude Opus 5 against 72.2% for GPT-5.2.
Is Claude Opus 5 better than GPT-5.2 for agents and tool use?
Claude Opus 5 scores higher in agentic tasks (64 vs 55 on the category index, where 50 is average).
Which is better for long documents?
GPT-5.2 scores higher on long-context benchmarks (66 vs 65). Claude Opus 5 accepts more context: 1,000,000 against 400,000 tokens for GPT-5.2.
Which has lower latency?
Claude Opus 5 (max) answers first: 68.7 s against 124.7 s to the first answer token, as Artificial Analysis measures it. Reasoning effort drives most of this: a higher setting thinks longer before it answers.
Which is faster, Claude Opus 5 or GPT-5.2?
GPT-5.2 streams faster: 81 against 51 output tokens per second.
Do independent benchmarks agree on Claude Opus 5 vs GPT-5.2?
Across the 22 benchmarks both have, Claude Opus 5 leads 20, GPT-5.2 leads 2. Every overall index that rates both puts Claude Opus 5 ahead.
When was Claude Opus 5 released?
Claude Opus 5 was released on 24 Jul 2026.