BenchLeader

Claude Opus 4.8 vs GPT-5

Full profiles: Claude Opus 4.8 (Anthropic) and GPT-5 (OpenAI): every benchmark, price and rank.

Updated · Data from 16 sources

As of 16 Nov 2026, Claude Opus 4.8 and GPT-5 are neck and neck on quality (61.1 vs 59.0 on the BenchLeader Index, inside the ±6.7 margin), and GPT-5 is 2.9× cheaper at $3.44 vs $10.00 per 1M tokens blended. Choose Claude Opus 4.8 for reasoning (64 vs 48), coding (62 vs 57), and maths (68 vs 65); choose GPT-5 for fast first answers (22.9 s vs 39.1 s) and instruction following (69 vs 62), long context (70 vs 63), and agents & tools (58 vs 57).

Key facts (as of 16 Nov 2026)

  • Claude Opus 4.8 scores 61.1 on the BenchLeader Index and GPT-5 scores 59.0 (BenchLeader, 16 Nov 2026).
  • Claude Opus 4.8 costs $10.00 per 1M tokens blended (list price, 16 Nov 2026).
  • GPT-5 costs $3.44 per 1M tokens blended (list price, 16 Nov 2026).
  • Of the 14 benchmarks both models have, Claude Opus 4.8 leads 12 (BenchLeader, 16 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
CodingClaude Opus 4.862 vs 57 category scoreMedium
Agents & tool useGPT-558 vs 57 category score; Terminal-Bench 49.6% vs 23.6%Medium
MathsClaude Opus 4.868 vs 65 category score; OTIS Mock AIME 98.3% vs 87.2%Medium
ReasoningClaude Opus 4.864 vs 48 category score; GPQA Diamond 91.0% vs 85.3%High
Long documentsGPT-570 vs 63 category score; AA-LCR v1.1 76.0% vs 77.7%Medium
Following instructionsGPT-569 vs 62 category score; IFBench 70.6% vs 62.2%Medium
Lowest costGPT-5$3.44 vs $10.00 per 1M blended; agentic coding session $0.115 vs $0.400–
Fastest first answerGPT-522.9 s (GPT-5 (medium)) vs 39.1 s (Claude Opus 4.8 (max)) 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 (max) and GPT-5 (medium) are neck and neck on quality (61.1 vs 59.0, within the ±6.7 margin).
  • Claude Opus 4.8 (max) is stronger in coding, maths, reasoning.
  • GPT-5 (medium) is stronger in agents & tools, instruction following, long context.
  • GPT-5 (medium) is 2.9× cheaper ($3.44 vs $10.00 per 1M blended).

At a glance

SpecClaude Opus 4.8GPT-5
DeveloperAnthropicOpenAI
Released28 May 20267 Aug 2025
Context window (tokens)1,000,000400,000
Compared atClaude Opus 4.8 (max)GPT-5 (medium)
Open weightsNoNo
Price in / out / cached input per 1M$5.00 / $25.00 / $0.500$1.25 / $10.00 / $0.125

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 (max)GPT-5 (medium)Leader
Reasoning64.147.9Claude Opus 4.8
Coding61.957.4Claude Opus 4.8
Agents & tools56.958.1GPT-5
Maths67.765.4Claude Opus 4.8
Knowledge61.0–not comparable
Instruction following62.169.4GPT-5
Multimodal–56.6not comparable
Long context63.470.4GPT-5

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 & toolsMathsInstructionfollowingLong contextClaude Opus 4.8, Reasoning: 64.1Claude Opus 4.8, Coding: 61.9Claude Opus 4.8, Agents & tools: 56.9Claude Opus 4.8, Maths: 67.7Claude Opus 4.8, Instruction following: 62.1Claude Opus 4.8, Long context: 63.4GPT-5, Reasoning: 47.9GPT-5, Coding: 57.4GPT-5, Agents & tools: 58.1GPT-5, Maths: 65.4GPT-5, Instruction following: 69.4GPT-5, Long context: 70.4

Not drawn, measured for fewer than two of these models: Knowledge, Multimodal, Human preference.

Model, click to add or removeIndex

Where sources disagree

Across the 14 benchmarks both have, Claude Opus 4.8 leads 12, GPT-5 leads 2. Every overall index that rates both puts Claude Opus 4.8 ahead.

Overall indexClaude Opus 4.8 (max)GPT-5 (medium)Leader
BenchLeader Index61.159.0neck and neck
Arena Text1482†1435Claude 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 (max)GPT-5 (medium)
Blended price per 1M tokens$10.00$3.44
Input / output per 1M$5.00 / $25.00$1.25 / $10.00
Cached input per 1M$0.500$0.125
Price per task: chat reply$0.0095$0.0035
Price per task: summarize a 30-page report$0.075$0.021
Price per task: code edit$0.068$0.022
Price per task: agentic coding session$0.400$0.115
Price per task: structured extraction$0.015$0.0045
Agentic coding session, input mostly cached$0.198$0.064
Output speed85 tok/s82 tok/s
Time to first answer39.1 s22.9 s
Time to a complete answer, last measured 13 Nov 202681.0 s66.2 s

Each model is compared at its best-ranked reasoning-effort setting. Claude Opus 4.8 (max) scores 61.1 and takes 39 s to its first answer token; Claude Opus 4.8 (high) scores 60.4 in 1 s, Claude Opus 4.8 scores 58.7 in 1 s. GPT-5 (medium) scores 59.0 and takes 23 s to its first answer token; GPT-5 (high) scores 58.2 in 49 s, GPT-5 scores 56.6 in 5 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

173 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 (max)GPT-5 (medium)
BenchLeader IndexBenchLeader61.159.0
Agents & tools scoreBenchLeader56.958.1
Coding scoreBenchLeader61.957.4
Instruction following scoreBenchLeader62.169.4
Knowledge scoreBenchLeader61.0–
Long context scoreBenchLeader63.470.4
Maths scoreBenchLeader67.765.4
Reasoning scoreBenchLeader64.147.9
Multimodal scoreBenchLeader–56.6
Blended price $/MBenchLeader$10.00$3.44
Output speedBenchLeader85 tok/s82 tok/s
Time to first answerBenchLeader39.1 s22.9 s
Context windowBenchLeader1,000,000 tokens400,000 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub91.0%85.3%
Humanity's Last ExamScale AI / CAIS–25.3%†
SimpleBenchSimpleBench64.8%†56.7%†
Arena Hard PromptsArena (LMArena)1505†1449†
LiveBench 1.0 ReasoningLiveBench89.2%–
GPQA Diamond (AA)Artificial Analysis92.0%84.2%
Humanity's Last Exam (AA)Artificial Analysis48.7%25.4%
GPQA Diamond (Vals)Vals AI92.4%85.6%†
EnigmaEvalScale AI SEAL23.5%†–
Kagi LLM BenchmarkKagi LLM Benchmark88.8%†72.7%†
GPQA Diamond (HELM)HELM Capabilities–79.1%†
ARC-AGI-1ARC Prize92.5%56.2%
ARC-AGI-2ARC Prize72.1%†7.5%
ARC-AGI-3ARC Prize1.5%†–
CritPtArtificial Analysis20.9%0.0%
CritPt v2 hard subset (AA)Artificial Analysis–11.5%†
Arena ExpertArena (LMArena)1514†1445†
Chess PuzzlesEpoch AI Benchmarking Hub52.0%32.0%
Mystery Game PuzzlesEpoch AI Benchmarking Hub36.0%15.0%
LMCAEpoch AI Benchmarking Hub57.5%40.0%†
DTBenchEpoch AI Benchmarking Hub94.9%90.7%†
ForecastBenchForecastBench66.1%65.0%†
BTF-3Epoch AI Benchmarking Hub14.0%†–
Coding
SWE-bench Verified (Epoch)Epoch AI Benchmarking Hub–71.5%
SciCodeSciCode53.5%42.9%†
Show all 173 benchmarks
MetricPublisherClaude Opus 4.8 (max)GPT-5 (medium)
Coding
WeirdMLWeirdML70.5%†39.8%†
FrontierCodeCognition46.5%†–
GSO-BenchGSO-Bench47.1%†6.9%†
Arena CodingArena (LMArena)1529†1462†
Arena WebDevArena (LMArena)1536†1417
LiveBench 1.0 CodingLiveBench81.8%–
SciCode (AA)Artificial Analysis54.4%–
LiveCodeBenchVals AI87.8%85.9%†
SWE-bench (Vals)Vals AI88.6%69.0%†
SWE-Bench ProScale AI SEAL–41.8%†
Aider PolyglotAider polyglot leaderboard–86.7%
SWE-bench Verified (bash only)SWE-bench–65.0%
SWE-bench Verified (any scaffold)SWE-bench–74.4%†
Code MigrationVals AI47.3%–
ProgramBenchVals AI1.0%–
Vibe Code Bench v1.1Vals AI82.7%20.1%†
SWE-Bench Pro (private)Scale AI SEAL–14.9%†
SWE Atlas v1.0: Codebase QnAScale AI SEAL57.3%†–
SWE Atlas v1.0: RefactoringScale AI SEAL46.7%†–
SWE Atlas v1.0: Test WritingScale AI SEAL49.6%†–
MirrorCodeEpoch AI Benchmarking Hub65.6%4.4%†
Surface Evolver BenchEpoch AI Benchmarking Hub87.5%†–
DeepSWE v1.1Epoch AI Benchmarking Hub59.0%–
ALE-BenchEpoch AI Benchmarking Hub1563.8†1162.5†
AlgoTuneAlgoTune–1.7†
Terminal-Bench 4.0 (AA)Artificial Analysis21.7%–
Terminal-Bench 2.1 (AA)Artificial Analysis84.6%35.2%†
GameBench 2 OverallDuelLab GameBench 249.4†–
GameBench 2 by reasoning settingDuelLab GameBench 245.1†38.0
Design Arena WebsiteDesign Arena1250†1174†
LiveCodeBench (AA)Artificial Analysis–70.3%
Agents & tools
Terminal-BenchTerminal-Bench23.6%49.6%
OSWorld-Verified 2.0OSWorld20.6%–
GDPvalOpenAI–34.8%
Remote Labor IndexScale AI / CAIS8.3%†1.7%†
APEX-AgentsMercor48.9%–
LiveBench Agentic CodingLiveBench50.5%–
Terminal-Bench HardArtificial Analysis58.3%37.9%
τ²-Bench Telecom (AA)Artificial Analysis94.4%86.5%
Terminal-Bench 2.1 (Vals)Vals AI71.9%–
MCP AtlasScale AI SEAL82.2%–
HiL-BenchScale AI SEAL35.3%†–
τ³-bench Bankingτ²-bench39.7%–
GDPval-AA v2.1Artificial Analysis1461925†
τ³-Banking (AA)Artificial Analysis34.2%22.1%†
Analyst Agent (AA)Artificial Analysis45.0%–
Finance Agent v2Vals AI53.9%–
Harvey's Legal Agent Benchmark v1Vals AI9.6%–
Legal Research BenchVals AI43.8%–
Poker AgentVals AI–1103.2%†
SkillsBenchVals AI59.2%–
Tax Agent BenchVals AI30.0%–
Terminal-Bench 2.0 (Vals)Vals AI70.0%37.1%†
Terminal-Bench 4.0 (Vals)Vals AI23.2%–
Terminal-Bench ScienceVals AI4.3%–
Time Horizon Index: KSPVals AI11.8%–
Arena SearchArena (LMArena)1194†1189†
BALROGBALROG–32.8%†
DeepResearch BenchDeepResearch Bench50.2%†48.6%
PostTrainBenchEpoch AI Benchmarking Hub31.0%–
METR Time HorizonsMETR–69.6%
GBAEvalEpoch AI Benchmarking Hub70.9%†–
Vending-Bench 2Andon Labs2992.3–
AutomationBenchArtificial Analysis45.6%–
GDP.pdf (AA)Artificial Analysis22.8%–
EnterpriseOps-GymArtificial Analysis44.0%–
AA-Briefcase v1.1Artificial Analysis1320–
Design Arena AgenticDesign Arena1226†–
BrowseComp-PlusBrowseComp-Plus–57.6%†
BrowseCompOpenAI–20.1%†
DeepSearchQAGoogle–59.4%†
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub80.0%55.4%†
FrontierMath Tier 4Epoch AI Benchmarking Hub56.1%21.9%†
OTIS Mock AIMEEpoch AI Benchmarking Hub98.3%87.2%
MATH Level 5Epoch AI Benchmarking Hub–97.9%
ProofBenchVals AI69.0%18.0%†
LiveBench MathematicsLiveBench94.3%–
AIME (Vals)Vals AI–93.4%†
MGSMVals AI–92.8%†
AIME 2026MathArena100.0%–
HMMT February 2026MathArena95.5%–
IMO 2025MathArena–38.1%†
MathArena ApexMathArena81.3%1.0%†
Omni-MATH (HELM)HELM Capabilities–64.7%†
MATH 500Vals AI–96.0%†
Arena MathsArena (LMArena)1476†1411†
AIME 2025 (AA)Artificial Analysis–91.7%
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub53.0%50.1%†
LiveBench 1.0 Data AnalysisLiveBench66.0%–
MMLU-ProVals AI89.6%86.5%†
LegalBenchVals AI83.6%86.0%†
CorpFinVals AI66.7%61.1%†
TaxEvalVals AI75.6%73.4%†
MedQAVals AI–96.3%†
PRBench FinanceScale AI SEAL–51.3%†
PRBench LegalScale AI SEAL–49.0%†
MultiNRCScale AI SEAL–52.1%†
MMLU-Pro (HELM)HELM Capabilities–86.3%†
CaseLaw v2Vals AI–66.5%†
Excel Modeling BenchmarkVals AI69.4%–
MedCodeVals AI53.2%49.6%†
MedScribeVals AI85.8%83.7%†
Public Benefits Bench v1.1Vals AI68.1%–
DrugDiscoveryBenchScale AI SEAL46.8%–
EBR-benchEpoch AI Benchmarking Hub28.6%12.7%†
GDP.pdfEpoch AI Benchmarking Hub24.0%–
Global-MMLU-Lite (AA)Artificial Analysis–90.4%
Instruction following
LiveBench LanguageLiveBench79.7%–
LiveBench Instruction FollowingLiveBench72.0%–
IFBenchArtificial Analysis62.2%70.6%
MultiChallengeScale AI SEAL–63.2%†
TutorBenchScale AI SEAL–55.3%†
IFEval (HELM)HELM Capabilities–87.5%†
WildBench (HELM)HELM Capabilities–85.7%†
Arena Instruction FollowingArena (LMArena)1479†1415†
Human preference
Arena TextArena (LMArena)1474†1427†
EQ-Bench 4EQ-Bench1268†–
EQ-Bench Creative Writing v3EQ-Bench1840†1626†
Arena Creative WritingArena (LMArena)1464†1389†
Arena Multi-turnArena (LMArena)1493†1449†
Arena Longer QueriesArena (LMArena)1499†1435†
Lech Mazur Creative WritingLech Mazur–86.0%
Multimodal
Arena VisionArena (LMArena)1289†1232†
MMMU-ProArtificial Analysis–74.3%
VISTAScale AI SEAL–49.7%†
MMMU-Pro (Vals)Vals AI86.6%81.5%†
MortgageTaxVals AI69.9%65.5%†
Humanity's Sixth SenseScale AI SEAL23.5%–
VTBScale AI SEAL–17.0%†
GeoBenchGeoBench81.0%†81.0%
VPCTEpoch AI Benchmarking Hub–63.2%
Blueprint-Bench 2Epoch AI Benchmarking Hub14.5%†–
Furniture AssemblyEpoch AI Benchmarking Hub42.5%–
Long context
Fiction.LiveBench 120kFiction.live–96.9%
AA-LCR v1.1Artificial Analysis77.7%76.0%
Arena DocumentArena (LMArena)1476†–
MLCRArtificial Analysis19.4%–
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub159.9†150†
LiveBench 1.0LiveBench76.2%–
AA Intelligence Index v4.3.2Artificial Analysis41.822.9
AA Progress Index v1Artificial Analysis318.4264.4
HELM Capabilities meanHELM Capabilities–80.7%†
Vals RSI IndexVals AI24.0%–
Vals Multimodal IndexVals AI70.9%–
Safety & honesty
FORTRESSScale AI SEAL18.2%17.0%†
MASKScale AI SEAL–79.3%†
DistressBenchScale AI SEAL71.4%†–
Metadata
AA Openness IndexArtificial Analysis–5.6

Data as of 2026-11-16. Best configuration of each model; every score links to its source on the model pages.

DuelLab GameBench 2, release gb2-20261111-7b598bb13de4 (https://benchmarks.duellab.org/releases/gb2-20261111-7b598bb13de4/), 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 (max): BenchLeader Index 60.3 → 61.1.
  • GPT-5 (medium): BenchLeader Index 58.2 → 59.0.
  • Claude Opus 4.8 (max): 27 new results (LiveCodeBench, MMLU-Pro, LegalBench…).
  • GPT-5 (medium): 1 new result (Aider Polyglot).
  • Claude Opus 4.8 (max): 1 new result (GDPval-AA v2.1).
  • GPT-5 (medium): 2 new results (Global-MMLU-Lite (AA), AIME 2025 (AA)); 1 score revision.
  • Claude Opus 4.8 (max): 1 score revision.
  • Claude Opus 4.8 (max): 1 new result (MirrorCode).
  • GPT-5 (medium): 1 score revision.
  • GPT-5 (medium): 1 score revision.

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

Claude Opus 4.8 vs GPT-5: questions

Is Claude Opus 4.8 better than GPT-5?
Claude Opus 4.8 (max) and GPT-5 (medium) are neck and neck on quality (61.1 vs 59.0, within the ±6.7 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 16 Nov 2026, so check the category scores for your use.
Claude Opus 4.8 vs GPT-5: which is cheaper, and will that change?
GPT-5 is cheaper today: $3.44 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 better for coding?
Claude Opus 4.8 scores higher in coding (62 vs 57 on the category index, where 50 is average).
Which is faster, Claude Opus 4.8 or GPT-5?
Claude Opus 4.8 streams faster (85 vs 82 output tokens per second, Artificial Analysis 7-day median).
Is Claude Opus 4.8 or GPT-5 better for agents and tool use?
GPT-5 scores higher in agentic tasks (58 vs 57 on the category index, where 50 is average). On Terminal-Bench, the top shared agents & tools benchmark, it is 23.6% for Claude Opus 4.8 against 49.6% for GPT-5.
More questions (4)
Which is better for long documents?
GPT-5 scores higher on long-context benchmarks (70 vs 63). Claude Opus 4.8 accepts more context: 1,000,000 against 400,000 tokens for GPT-5.
Which has lower latency?
GPT-5 answers first: 22.9 s against 39.1 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?
Across the 14 benchmarks both have, Claude Opus 4.8 leads 12, GPT-5 leads 2. 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.