BenchLeader

Claude Opus 4.7 vs GPT-5.4

Full profiles: Claude Opus 4.7 (Anthropic) and GPT-5.4 (OpenAI): every benchmark, price and rank.

Updated · Data from 15 sources

As of 10 Nov 2026, Claude Opus 4.7 and GPT-5.4 are neck and neck on quality (63.2 vs 63.2 on the BenchLeader Index, inside the ±3.8 margin), and GPT-5.4 is 1.8× cheaper at $5.63 vs $10.00 per 1M tokens blended. Choose Claude Opus 4.7 for multimodal (67 vs 61), knowledge (62 vs 59), and agents & tools (65 vs 63) and fast first answers (1.0 s vs 111.7 s); choose GPT-5.4 for coding (65 vs 61), where it also streams ~1.5× faster.

Key facts (as of 10 Nov 2026)

  • Claude Opus 4.7 scores 63.2 on the BenchLeader Index and GPT-5.4 scores 63.2 (BenchLeader, 10 Nov 2026).
  • Claude Opus 4.7 costs $10.00 per 1M tokens blended (list price, 10 Nov 2026).
  • GPT-5.4 costs $5.63 per 1M tokens blended (list price, 10 Nov 2026).
  • GPT-5.4 streams ~1.5× faster than Claude Opus 4.7 (Artificial Analysis, 7-day median, 10 Nov 2026).
  • Of the 24 benchmarks both models have, Claude Opus 4.7 leads 14 (BenchLeader, 10 Nov 2026).

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
CodingGPT-5.465 vs 61 category score; WeirdML 77.7% vs 76.4%Medium
Agents & tool useClaude Opus 4.765 vs 63 category score; Harvey's Legal Agent Benchmark v1 6.7% vs 0.0%Medium
MathsClaude Opus 4.767 vs 65 category score; AIME (Vals) 96.3% vs 96.7%Medium
ReasoningEither65 vs 66 category score; Humanity's Last Exam 36.2% vs 36.2%Either
KnowledgeClaude Opus 4.762 vs 59 category score; MMLU-Pro 89.9% vs 87.5%Medium
Images and other mediaClaude Opus 4.767 vs 61 category score; MortgageTax 70.3% vs 68.3%Medium
Chat quality (human preference)–Only Claude Opus 4.7 has an Arena rating (67 category score)Not comparable
Lowest costGPT-5.4$5.63 vs $10.00 per 1M blended; agentic coding session $0.210 vs $0.400–
Fastest first answerClaude Opus 4.71.0 s (Claude Opus 4.7) vs 111.7 s (GPT-5.4 (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 4.7 and GPT-5.4 (xhigh) are neck and neck on quality (63.2 vs 63.2, within the ±3.8 margin).
  • Claude Opus 4.7 is stronger in agents & tools, human preference, knowledge, maths, multimodal.
  • GPT-5.4 (xhigh) is stronger in coding, reasoning, instruction following, long context.
  • GPT-5.4 (xhigh) is 1.8× cheaper ($5.63 vs $10.00 per 1M blended).
  • GPT-5.4 (xhigh) streams 1.6× faster (76 vs 48 tokens per second).

At a glance

SpecClaude Opus 4.7GPT-5.4
DeveloperAnthropicOpenAI
Released16 Apr 20265 Mar 2026
Context window (tokens)1,000,0001,050,000
Compared atClaude Opus 4.7GPT-5.4 (xhigh)
Open weightsNoNo
Price in / out / cached input per 1M$5.00 / $25.00 / $0.500$2.50 / $15.00 / $0.250

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 4.7GPT-5.4 (xhigh)Leader
Reasoning65.065.8level
Coding61.364.8GPT-5.4
Agents & tools65.163.0Claude Opus 4.7
Maths66.765.1Claude Opus 4.7
Knowledge62.458.6Claude Opus 4.7
Instruction following–72.4not comparable
Human preference67.3–not comparable
Multimodal67.160.9Claude Opus 4.7
Long context–65.7not comparable

On one chart

Each domain on the index's own scale, where 50 is an average model. Click a domain to see the benchmarks behind it. Pick up to 5 models from the list.

2550 avg75ReasoningCodingAgents & toolsMathsKnowledgeMultimodalClaude Opus 4.7, Reasoning: 65.0Claude Opus 4.7, Coding: 61.3Claude Opus 4.7, Agents & tools: 65.1Claude Opus 4.7, Maths: 66.7Claude Opus 4.7, Knowledge: 62.4Claude Opus 4.7, Multimodal: 67.1GPT-5.4, Reasoning: 65.8GPT-5.4, Coding: 64.8GPT-5.4, Agents & tools: 63.0GPT-5.4, Maths: 65.1GPT-5.4, Knowledge: 58.6GPT-5.4, Multimodal: 60.9

Not drawn, measured for fewer than two of these models: Instruction following, Long context, Human preference.

ModelIndex

Where sources disagree

Across the 24 benchmarks both have, Claude Opus 4.7 leads 14, GPT-5.4 leads 9 and 1 is a tie. Every overall index that rates both puts Claude Opus 4.7 ahead.

Overall indexClaude Opus 4.7GPT-5.4 (xhigh)Leader
BenchLeader Index63.263.2neck and neck
Arena Text14941475†Claude Opus 4.7

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. Cost, tokens and time per benchmark task are measured: Artificial Analysis’ averages over its whole Intelligence Index run.

MeasureClaude Opus 4.7GPT-5.4 (xhigh)
Blended price per 1M tokens$10.00$5.63
Input / output per 1M$5.00 / $25.00$2.50 / $15.00
Cached input per 1M$0.500$0.250
Price per task: chat reply$0.0095$0.0055
Price per task: summarize a 30-page report$0.075$0.039
Price per task: code edit$0.068$0.037
Price per task: agentic coding session$0.400$0.210
Price per task: structured extraction$0.015$0.0080
Agentic coding session, input mostly cached$0.198$0.109
Output speed48 tok/s76 tok/s
Time to first answer1.0 s111.7 s
Time to a complete answer–195.8 s

Each model is compared at its best-ranked reasoning-effort setting. Claude Opus 4.7 scores 63.2 and takes 1 s to its first answer token; Claude Opus 4.7 (high) scores 60.9 in 1 s, Claude Opus 4.7 (max) scores 59.5 in 17 s. GPT-5.4 (xhigh) scores 63.2 and takes 112 s to its first answer token; GPT-5.4 (low) scores 58.8 in 4 s, GPT-5.4 (high) scores 58.8 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

127 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 4.7GPT-5.4 (xhigh)
BenchLeader IndexBenchLeader63.263.2
Agents & tools scoreBenchLeader65.163.0
Coding scoreBenchLeader61.364.8
Human preference scoreBenchLeader67.3–
Knowledge scoreBenchLeader62.458.6
Maths scoreBenchLeader66.765.1
Multimodal scoreBenchLeader67.160.9
Reasoning scoreBenchLeader65.065.8
Instruction following scoreBenchLeader–72.4
Long context scoreBenchLeader–65.7
Blended price $/MBenchLeader$10.00$5.63
Output speedBenchLeader48 tok/s76 tok/s
Time to first answerBenchLeader1.0 s111.7 s
Context windowBenchLeader1,000,000 tokens1,050,000 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub86.4%†93.3%
Humanity's Last ExamScale AI / CAIS36.2%36.2%
SimpleBenchSimpleBench61.7%–
Arena Hard PromptsArena (LMArena)15191487†
LiveBench 1.0 ReasoningLiveBench87.2%†88.1%
GPQA Diamond (AA)Artificial Analysis91.4%†92.0%
Humanity's Last Exam (AA)Artificial Analysis42.3%†43.7%
GPQA Diamond (Vals)Vals AI90.2%91.7%
Kagi LLM BenchmarkKagi LLM Benchmark73.3%63.8%†
ARC-AGI-1ARC Prize–93.7%
ARC-AGI-2ARC Prize–74.0%
ARC-AGI-3ARC Prize0.2%†0.2%†
CritPtArtificial Analysis12.0%†23.4%
Chess PuzzlesEpoch AI Benchmarking Hub41.0%†48.0%
Mystery Game PuzzlesEpoch AI Benchmarking Hub13.0%37.0%
CL-benchEpoch AI Benchmarking Hub–27.9%
CL-bench LifeEpoch AI Benchmarking Hub–21.7%
LMCAEpoch AI Benchmarking Hub52.2%†52.0%
DTBenchEpoch AI Benchmarking Hub94.7%†94.4%
ForecastBenchForecastBench62.8%63.0%†
Coding
SWE-bench Verified (Epoch)Epoch AI Benchmarking Hub83.5%†76.9%†
SciCodeSciCode54.5%†56.6%
WeirdMLWeirdML76.4%77.7%
FrontierCodeCognition38.5%–
GSO-BenchGSO-Bench44.1%31.4%
Show all 127 benchmarks
MetricPublisherClaude Opus 4.7GPT-5.4 (xhigh)
Coding
Arena CodingArena (LMArena)15471511†
Arena WebDevArena (LMArena)15551400†
LiveBench 1.0 CodingLiveBench82.1%†77.5%
LiveCodeBenchVals AI85.1%84.1%
SWE-bench (Vals)Vals AI82.0%78.2%
SWE-Bench ProScale AI SEAL–59.1%
Code MigrationVals AI43.9%35.0%
ProgramBenchVals AI0.0%0.0%
Vibe Code Bench v1.1Vals AI71.0%67.4%
SWE-Bench Pro (private)Scale AI SEAL–59.1%
SWE Atlas: Codebase QnAScale AI SEAL40.3%40.8%
SWE Atlas: RefactoringScale AI SEAL48.6%44.3%
SWE Atlas: Test WritingScale AI SEAL38.5%44.4%
MirrorCodeEpoch AI Benchmarking Hub31.1%†15.6%†
DeepSWE v1.1Epoch AI Benchmarking Hub–51.8%
ALE-BenchEpoch AI Benchmarking Hub1323.01607†
AlgoTuneAlgoTune–1.9†
Terminal-Bench 2.1 (AA)Artificial Analysis83.2%†78.3%
GameBench 2 OverallDuelLab GameBench 2–53.4†
GameBench 2 by reasoning settingDuelLab GameBench 2–61.8
Design Arena WebsiteDesign Arena–1194†
Agents & tools
Terminal-BenchTerminal-Bench80.2%81.8%†
OSWorld-Verified 2.0OSWorld18.2%†–
APEX-AgentsMercor49.2%†52.4%†
LiveBench Agentic CodingLiveBench50.7%†53.8%
Terminal-Bench HardArtificial Analysis51.5%†57.6%
τ²-Bench Telecom (AA)Artificial Analysis88.6%†87.1%
Terminal-Bench 2.1 (Vals)Vals AI68.5%–
MCP AtlasScale AI SEAL79.1%†70.6%
HiL-BenchScale AI SEAL41.7%9.7%†
τ³-bench Bankingτ²-bench40.2%†39.4%
τ³-Banking (AA)Artificial Analysis34.6%†39.6%
ITBench SRE (AA)Artificial Analysis46.7%†–
Analyst Agent (AA)Artificial Analysis43.8%†–
APEX-Agents (AA)Artificial Analysis–33.3%
Finance Agent v2Vals AI51.5%–
Harvey's Legal Agent Benchmark v1Vals AI6.7%0.0%
Legal Research BenchVals AI38.5%–
SkillsBenchVals AI–51.7%
Tax Agent BenchVals AI23.7%–
Terminal-Bench 2.0 (Vals)Vals AI68.5%58.4%†
Arena SearchArena (LMArena)12101196†
DeepResearch BenchDeepResearch Bench–35.1%†
PostTrainBenchEpoch AI Benchmarking Hub28.6%†19.0%†
ExploitBenchEpoch AI Benchmarking Hub26.5%–
METR Time HorizonsMETR–74.3%
GBAEvalEpoch AI Benchmarking Hub43.8%45.1%†
Vending-Bench 2Andon Labs10936.86144.2†
Design Arena AgenticDesign Arena–1035†
DeepSearchQAGoogle–63.7%†
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub70.2%†78.6%
FrontierMath Tier 4Epoch AI Benchmarking Hub31.7%†49.0%
OTIS Mock AIMEEpoch AI Benchmarking Hub86.7%†95.3%
ProofBenchVals AI54.0%†56.0%
LiveBench MathematicsLiveBench92.8%†94.2%
AIME (Vals)Vals AI96.3%96.7%
AIME 2026MathArena95.8%†99.2%
HMMT February 2026MathArena93.9%†97.7%
USAMO 2026MathArena–95.2%
MathArena ApexMathArena40.6%†54.2%
Arena MathsArena (LMArena)14901459†
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub51.7%†45.1%
LiveBench 1.0 Data AnalysisLiveBench78.3%†79.3%
MMLU-ProVals AI89.9%87.5%
LegalBenchVals AI85.3%86.0%
CorpFinVals AI66.1%65.3%
TaxEvalVals AI75.3%74.0%
MedQAVals AI–96.1%
PRBench FinanceScale AI SEAL–45.6%†
PRBench LegalScale AI SEAL–44.4%†
MultiNRCScale AI SEAL–58.3%†
CaseLaw v2Vals AI68.4%63.8%
Excel Modeling BenchmarkVals AI63.7%–
MedCodeVals AI54.9%41.3%
MedScribeVals AI83.0%77.5%
EBR-benchEpoch AI Benchmarking Hub19.1%†25.4%
GDP.pdfEpoch AI Benchmarking Hub21.0%†–
Instruction following
LiveBench LanguageLiveBench77.9%†82.6%
LiveBench Instruction FollowingLiveBench66.7%†70.2%
IFBenchArtificial Analysis58.6%†74.0%
Arena Instruction FollowingArena (LMArena)14931460†
Human preference
Arena TextArena (LMArena)14941465†
EQ-Bench 4EQ-Bench12931258†
Arena Creative WritingArena (LMArena)14821433†
Arena Multi-turnArena (LMArena)15141480†
Arena Longer QueriesArena (LMArena)15081477†
Multimodal
Arena VisionArena (LMArena)13191292†
MMMU-ProArtificial Analysis78.8%†78.4%
VISTAScale AI SEAL–50.9%†
MMMU-Pro (Vals)Vals AI85.5%87.5%
MortgageTaxVals AI70.3%68.3%
VTBScale AI SEAL–29.2%†
Blueprint-Bench 2Epoch AI Benchmarking Hub24.5%27.1%†
Long context
AA-LCR v1.1Artificial Analysis78.7%†82.0%
Arena DocumentArena (LMArena)14941471†
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub157.6157.8†
LiveBench 1.0LiveBench76.5%†78.0%
AA Intelligence Index v4.3.2Artificial Analysis40.7†39.0
AA Progress Index v1Artificial Analysis312.5†311.6
Vals RSI IndexVals AI19.1%†15.5%
Vals Multimodal IndexVals AI67.4%–
Safety & honesty
MASKScale AI SEAL–89.7%†

Data as of 2026-11-10. Best configuration of each model; every score links to its source on the model pages.

DuelLab GameBench 2, release gb2-20261103-eaea31df94e6 (https://benchmarks.duellab.org/releases/gb2-20261103-eaea31df94e6/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.

What changed

  • GPT-5.4 (xhigh): BenchLeader Index 63.7 → 63.2.
  • Claude Opus 4.7: 1 score revision.
  • GPT-5.4 (xhigh): 1 score revision.
  • GPT-5.4 (xhigh): 1 new result (AA Progress Index v1).
  • Claude Opus 4.7: 1 score revision.
  • Claude Opus 4.7: 1 new result (Harvey's Legal Agent Benchmark v1).
  • GPT-5.4 (xhigh): 2 new results (Harvey's Legal Agent Benchmark v1, Vals RSI Index).
  • Claude Opus 4.7: 1 score revision.
  • Claude Opus 4.7: 1 score revision.
  • GPT-5.4 (xhigh): 2 new results (USAMO 2026, τ³-bench Banking).

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

Claude Opus 4.7 vs GPT-5.4: questions

Is Claude Opus 4.7 better than GPT-5.4?
Claude Opus 4.7 and GPT-5.4 (xhigh) are neck and neck on quality (63.2 vs 63.2, within the ±3.8 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 10 Nov 2026, so check the category scores for your use.
Claude Opus 4.7 vs GPT-5.4: which is cheaper, and will that change?
GPT-5.4 is cheaper today: $5.63 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 4.7 or GPT-5.4 better for coding?
GPT-5.4 scores higher in coding (65 vs 61 on the category index, where 50 is average). On LiveCodeBench, the top shared coding benchmark, it is 85.1% for Claude Opus 4.7 against 84.1% for GPT-5.4.
Which is faster, Claude Opus 4.7 or GPT-5.4?
GPT-5.4 streams ~1.5× faster (76 vs 48 output tokens per second, Artificial Analysis 7-day median).
Is Claude Opus 4.7 or GPT-5.4 better for agents and tool use?
Claude Opus 4.7 scores higher in agentic tasks (65 vs 63 on the category index, where 50 is average).
More questions (4)
Which is better for long documents?
Both take about 1.1M tokens: Claude Opus 4.7 1,000,000, GPT-5.4 1,050,000.
Which has lower latency?
Claude Opus 4.7 answers first: 1.0 s against 111.7 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.
Do independent benchmarks agree on Claude Opus 4.7 vs GPT-5.4?
Across the 24 benchmarks both have, Claude Opus 4.7 leads 14, GPT-5.4 leads 9 and 1 is a tie. Every overall index that rates both puts Claude Opus 4.7 ahead.
When was Claude Opus 4.7 released?
Claude Opus 4.7 was released on 16 Apr 2026.