BenchLeader

Claude Opus 4.8 vs GPT-5.4

Full profiles: Claude Opus 4.8 (Anthropic) and GPT-5.4 (OpenAI): every benchmark, price and rank.

Updated · Data from 13 sources

As of 12 Nov 2026, Claude Opus 4.8 and GPT-5.4 are neck and neck on quality (60.4 vs 63.1 on the BenchLeader Index, inside the ±6.2 margin), and GPT-5.4 is 1.8× cheaper at $5.63 vs $10.00 per 1M tokens blended. Choose Claude Opus 4.8 for multimodal (64 vs 61) and maths (68 vs 65) and fast first answers (0.8 s vs 111.3 s); choose GPT-5.4 for reasoning (66 vs 60) and coding (65 vs 61).

Key facts (as of 12 Nov 2026)

  • Claude Opus 4.8 scores 60.4 on the BenchLeader Index and GPT-5.4 scores 63.1 (BenchLeader, 12 Nov 2026).
  • Claude Opus 4.8 costs $10.00 per 1M tokens blended (list price, 12 Nov 2026).
  • GPT-5.4 costs $5.63 per 1M tokens blended (list price, 12 Nov 2026).
  • Of the 3 benchmarks both models have, GPT-5.4 leads 2 (BenchLeader, 12 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; DeepSWE v1.1 51.8% vs 51.8%Medium
MathsClaude Opus 4.868 vs 65 category scoreMedium
ReasoningGPT-5.466 vs 60 category score; ARC-AGI-2 74.0% vs 72.1%Medium
Images and other mediaClaude Opus 4.864 vs 61 category scoreMedium
Chat quality (human preference)–Only Claude Opus 4.8 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 4.80.8 s (Claude Opus 4.8 (high)) vs 111.3 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 4.8 (high) and GPT-5.4 (xhigh) are neck and neck on quality (60.4 vs 63.1, within the ±6.2 margin).
  • Claude Opus 4.8 (high) is stronger in maths, multimodal.
  • GPT-5.4 (xhigh) is stronger in coding, reasoning.
  • GPT-5.4 (xhigh) is 1.8× cheaper ($5.63 vs $10.00 per 1M blended).

At a glance

SpecClaude Opus 4.8GPT-5.4
DeveloperAnthropicOpenAI
Released28 May 20265 Mar 2026
Context window (tokens)1,000,0001,050,000
Compared atClaude Opus 4.8 (high)GPT-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 4.8 (high)GPT-5.4 (xhigh)Leader
Reasoning59.865.6GPT-5.4
Coding61.064.7GPT-5.4
Agents & tools–63.0not comparable
Maths67.565.0Claude Opus 4.8
Knowledge–58.6not comparable
Instruction following–72.4not comparable
Human preference67.2–not comparable
Multimodal64.060.9Claude Opus 4.8
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 avg75ReasoningCodingMathsMultimodalClaude Opus 4.8, Reasoning: 59.8Claude Opus 4.8, Coding: 61.0Claude Opus 4.8, Maths: 67.5Claude Opus 4.8, Multimodal: 64.0GPT-5.4, Reasoning: 65.6GPT-5.4, Coding: 64.7GPT-5.4, Maths: 65.0GPT-5.4, Multimodal: 60.9

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

Model, click to add or removeIndex

Where sources disagree

Across the 3 benchmarks both have, Claude Opus 4.8 leads 0, GPT-5.4 leads 2 and 1 is a tie. Every overall index that rates both puts Claude Opus 4.8 ahead.

Overall indexClaude Opus 4.8 (high)GPT-5.4 (xhigh)Leader
BenchLeader Index60.463.1neck and neck
Arena Text14821475†Claude Opus 4.8

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 4.8 (high)GPT-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 speed68 tok/s68 tok/s
Time to first answer0.8 s111.3 s
Time to a complete answer–188.0 s

Each model is compared at its best-ranked reasoning-effort setting. Claude Opus 4.8 (high) scores 60.4 and takes 1 s to its first answer token; Claude Opus 4.8 (max) scores 59.9 in 36 s, Claude Opus 4.8 scores 59.6 in 1 s. GPT-5.4 (xhigh) scores 63.1 and takes 111 s to its first answer token; GPT-5.4 (low) scores 58.8 in 3 s, GPT-5.4 (high) scores 58.7 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

143 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 4.8 (high)GPT-5.4 (xhigh)
BenchLeader IndexBenchLeader60.463.1
Coding scoreBenchLeader61.064.7
Human preference scoreBenchLeader67.2–
Maths scoreBenchLeader67.565.0
Multimodal scoreBenchLeader64.060.9
Reasoning scoreBenchLeader59.865.6
Agents & tools scoreBenchLeader–63.0
Instruction following scoreBenchLeader–72.4
Knowledge scoreBenchLeader–58.6
Long context scoreBenchLeader–65.7
Blended price $/MBenchLeader$10.00$5.63
Output speedBenchLeader68 tok/s68 tok/s
Time to first answerBenchLeader0.8 s111.3 s
Context windowBenchLeader1,000,000 tokens1,050,000 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub91.0%†93.3%
Humanity's Last ExamScale AI / CAIS–36.2%
SimpleBenchSimpleBench64.8%†–
Arena Hard PromptsArena (LMArena)15131487†
LiveBench 1.0 ReasoningLiveBench89.2%†88.1%
GPQA Diamond (AA)Artificial Analysis92.0%†92.0%
Humanity's Last Exam (AA)Artificial Analysis48.7%†43.7%
GPQA Diamond (Vals)Vals AI92.4%†91.7%
EnigmaEvalScale AI SEAL23.5%†–
Kagi LLM BenchmarkKagi LLM Benchmark88.8%†63.8%†
ARC-AGI-1ARC Prize92.0%93.7%
ARC-AGI-2ARC Prize72.1%74.0%
ARC-AGI-3ARC Prize1.5%0.2%†
CritPtArtificial Analysis20.9%†23.4%
Chess PuzzlesEpoch AI Benchmarking Hub52.0%†48.0%
Mystery Game PuzzlesEpoch AI Benchmarking Hub36.0%†37.0%
CL-benchEpoch AI Benchmarking Hub–27.9%
CL-bench LifeEpoch AI Benchmarking Hub–21.7%
LMCAEpoch AI Benchmarking Hub57.5%†52.0%
DTBenchEpoch AI Benchmarking Hub94.9%†94.4%
ForecastBenchForecastBench62.4%†63.0%†
BTF-3Epoch AI Benchmarking Hub14.0%–
Coding
SWE-bench Verified (Epoch)Epoch AI Benchmarking Hub–76.9%†
SciCodeSciCode53.5%†56.6%
WeirdMLWeirdML70.5%†77.7%
Show all 143 benchmarks
MetricPublisherClaude Opus 4.8 (high)GPT-5.4 (xhigh)
Coding
FrontierCodeCognition46.5%†–
GSO-BenchGSO-Bench47.1%†31.4%
Arena CodingArena (LMArena)15331511†
Arena WebDevArena (LMArena)15561399†
LiveBench 1.0 CodingLiveBench81.8%†77.5%
SciCode (AA)Artificial Analysis54.4%†–
LiveCodeBenchVals AI87.8%†84.1%
SWE-bench (Vals)Vals AI88.6%†78.2%
SWE-Bench ProScale AI SEAL–59.1%
Code MigrationVals AI47.3%†35.0%
ProgramBenchVals AI1.0%†0.0%
Vibe Code Bench v1.1Vals AI82.7%†67.4%
SWE-Bench Pro (private)Scale AI SEAL–59.1%
SWE Atlas: Codebase QnAScale AI SEAL57.3%†40.8%
SWE Atlas: RefactoringScale AI SEAL46.7%†44.3%
SWE Atlas: Test WritingScale AI SEAL49.6%†44.4%
MirrorCodeEpoch AI Benchmarking Hub65.6%†23.3%
Surface Evolver BenchEpoch AI Benchmarking Hub87.5%–
DeepSWE v1.1Epoch AI Benchmarking Hub51.8%51.8%
ALE-BenchEpoch AI Benchmarking Hub1563.81607†
AlgoTuneAlgoTune–1.9†
Terminal-Bench 4.0 (AA)Artificial Analysis21.7%†–
Terminal-Bench 2.1 (AA)Artificial Analysis84.6%†78.3%
GameBench 2 OverallDuelLab GameBench 249.6†54.0†
GameBench 2 by reasoning settingDuelLab GameBench 246.0†62.2
Design Arena WebsiteDesign Arena1254†1193†
Agents & tools
Terminal-BenchTerminal-Bench23.6%†81.8%†
OSWorld-Verified 2.0OSWorld20.6%†–
Remote Labor IndexScale AI / CAIS8.3%†–
APEX-AgentsMercor48.9%†52.4%†
LiveBench Agentic CodingLiveBench50.5%†53.8%
Terminal-Bench HardArtificial Analysis58.3%†57.6%
τ²-Bench Telecom (AA)Artificial Analysis94.4%†87.1%
Terminal-Bench 2.1 (Vals)Vals AI71.9%†–
MCP AtlasScale AI SEAL82.2%†70.6%
HiL-BenchScale AI SEAL35.3%†9.7%†
τ³-bench Bankingτ²-bench39.7%†39.4%
τ³-Banking (AA)Artificial Analysis34.2%†39.6%
Analyst Agent (AA)Artificial Analysis45.0%†–
APEX-Agents (AA)Artificial Analysis–33.3%
Finance Agent v2Vals AI53.9%†–
Harvey's Legal Agent Benchmark v1Vals AI9.6%†0.0%
Legal Research BenchVals AI43.8%†–
SkillsBenchVals AI59.2%†51.7%
Tax Agent BenchVals AI30.0%†–
Terminal-Bench 2.0 (Vals)Vals AI70.0%†58.4%†
Terminal-Bench 4.0 (Vals)Vals AI23.2%†–
Terminal-Bench ScienceVals AI4.3%†–
Time Horizon Index: KSPVals AI11.8%†–
Arena SearchArena (LMArena)1194†1196†
DeepResearch BenchDeepResearch Bench50.2%35.1%†
PostTrainBenchEpoch AI Benchmarking Hub30.7%17.8%†
METR Time HorizonsMETR–74.3%
GBAEvalEpoch AI Benchmarking Hub70.9%†45.1%†
Vending-Bench 2Andon Labs5787.4†6144.2†
AutomationBenchArtificial Analysis45.6%†–
GDP.pdf (AA)Artificial Analysis22.8%†–
EnterpriseOps-GymArtificial Analysis44.0%†–
AA-Briefcase v1.1Artificial Analysis1320†–
Design Arena AgenticDesign Arena1219†1035†
DeepSearchQAGoogle–63.7%†
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub80.0%†78.6%
FrontierMath Tier 4Epoch AI Benchmarking Hub56.1%†49.0%
OTIS Mock AIMEEpoch AI Benchmarking Hub98.3%†95.3%
ProofBenchVals AI69.0%†56.0%
LiveBench MathematicsLiveBench94.3%†94.2%
AIME (Vals)Vals AI–96.7%
AIME 2026MathArena100.0%†99.2%
HMMT February 2026MathArena95.5%†97.7%
USAMO 2026MathArena–95.2%
MathArena ApexMathArena81.3%†54.2%
Arena MathsArena (LMArena)14921459†
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub53.0%†45.1%
LiveBench 1.0 Data AnalysisLiveBench66.0%†79.3%
MMLU-ProVals AI89.6%†87.5%
LegalBenchVals AI83.6%†86.0%
CorpFinVals AI66.7%†65.3%
TaxEvalVals AI75.6%†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 AI–63.8%
Excel Modeling BenchmarkVals AI69.4%†–
MedCodeVals AI53.2%†41.3%
MedScribeVals AI85.8%†77.5%
Public Benefits Bench v1.1Vals AI68.1%†–
DrugDiscoveryBenchScale AI SEAL46.8%†–
EBR-benchEpoch AI Benchmarking Hub28.6%†25.4%
GDP.pdfEpoch AI Benchmarking Hub24.0%†–
Instruction following
LiveBench LanguageLiveBench79.7%†82.6%
LiveBench Instruction FollowingLiveBench72.0%†70.2%
IFBenchArtificial Analysis62.2%†74.0%
Arena Instruction FollowingArena (LMArena)14921460†
Human preference
Arena TextArena (LMArena)14821465†
EQ-Bench 4EQ-Bench1268†1258†
Arena Creative WritingArena (LMArena)14701433†
Arena Multi-turnArena (LMArena)14971480†
Arena Longer QueriesArena (LMArena)15031477†
Multimodal
Arena VisionArena (LMArena)12951292†
MMMU-ProArtificial Analysis–78.4%
VISTAScale AI SEAL–50.9%†
MMMU-Pro (Vals)Vals AI86.6%†87.5%
MortgageTaxVals AI69.9%†68.3%
VTBScale AI SEAL–29.2%†
GeoBenchGeoBench81.0%–
Blueprint-Bench 2Epoch AI Benchmarking Hub14.5%†27.1%†
Long context
AA-LCR v1.1Artificial Analysis77.7%†82.0%
Arena DocumentArena (LMArena)14851471†
MLCRArtificial Analysis19.4%†–
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub159.9†157.8†
LiveBench 1.0LiveBench76.2%†78.0%
AA Intelligence Index v4.3.2Artificial Analysis41.8†39.0
AA Progress Index v1Artificial Analysis318.4†311.6
Vals RSI IndexVals AI24.0%†15.5%
Vals Multimodal IndexVals AI70.9%†–
Safety & honesty
FORTRESSScale AI SEAL18.2%†–
MASKScale AI SEAL–89.7%†

Data as of 2026-11-12. Best configuration of each model; every score links to its source on the model pages.

DuelLab GameBench 2, release gb2-20261110-2acac640a228 (https://benchmarks.duellab.org/releases/gb2-20261110-2acac640a228/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.

What changed

  • Claude Opus 4.8 (high): 1 score revision.
  • Claude Opus 4.8 (high): 1 new result (GeoBench).
  • GPT-5.4 (xhigh): 1 new result (MirrorCode).
  • GPT-5.4 (xhigh): BenchLeader Index 63.7 → 63.2.
  • GPT-5.4 (xhigh): 1 score revision.
  • GPT-5.4 (xhigh): 1 new result (AA Progress Index v1).
  • GPT-5.4 (xhigh): 2 new results (Harvey's Legal Agent Benchmark v1, Vals RSI Index).
  • Claude Opus 4.8 (high): BenchLeader Index 61.1 → 60.6.
  • GPT-5.4 (xhigh): 2 new results (USAMO 2026, τ³-bench Banking).
  • Claude Opus 4.8 (high): 1 score revision.

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

Claude Opus 4.8 vs GPT-5.4: questions

Is Claude Opus 4.8 better than GPT-5.4?
Claude Opus 4.8 (high) and GPT-5.4 (xhigh) are neck and neck on quality (60.4 vs 63.1, within the ±6.2 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 12 Nov 2026, so check the category scores for your use.
Claude Opus 4.8 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 4.8 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).
Which is faster, Claude Opus 4.8 or GPT-5.4?
GPT-5.4 streams faster (68 vs 68 output tokens per second, Artificial Analysis 7-day median).
Which is better for long documents?
Both take about 1.1M tokens: Claude Opus 4.8 1,000,000, GPT-5.4 1,050,000.
More questions (3)
Which has lower latency?
Claude Opus 4.8 answers first: 0.8 s against 111.3 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 4.8 vs GPT-5.4?
Across the 3 benchmarks both have, Claude Opus 4.8 leads 0, GPT-5.4 leads 2 and 1 is a tie. Every overall index that rates both puts Claude Opus 4.8 ahead.
When was Claude Opus 4.8 released?
Claude Opus 4.8 was released on 28 May 2026.