BenchLeader

Claude Opus 4.6 vs Claude Sonnet 5

Full profiles: Claude Opus 4.6 (Anthropic) and Claude Sonnet 5 (Anthropic): every benchmark, price and rank.

Updated · Data from 9 sources

As of 16 Nov 2026, Claude Opus 4.6 is ahead of Claude Sonnet 5 on quality (62.5 vs 59.0 on the BenchLeader Index), but Claude Sonnet 5 is 2.5× cheaper at $4.00 vs $10.00 per 1M tokens blended. Choose Opus 4.6 for multimodal (67 vs 61), human preference (70 vs 65), and coding (62 vs 60) and fast first answers (1.1 s vs 15.8 s); choose Sonnet 5 for maths (65 vs 63), where it also streams ~2× faster.

Key facts (as of 16 Nov 2026)

  • Claude Opus 4.6 scores 62.5 on the BenchLeader Index and Claude Sonnet 5 scores 59.0 (BenchLeader, 16 Nov 2026).
  • Claude Opus 4.6 costs $10.00 per 1M tokens blended (list price, 16 Nov 2026).
  • Claude Sonnet 5 costs $4.00 per 1M tokens blended (list price, 16 Nov 2026).
  • Claude Sonnet 5 streams ~2× faster than Claude Opus 4.6 (Artificial Analysis, 7-day median, 16 Nov 2026).
  • Of the 12 benchmarks both models have, Claude Opus 4.6 leads 12 (BenchLeader, 16 Nov 2026).
  • On Arena WebDev, Claude Opus 4.6 is rated 1547 and Claude Sonnet 5 1539 (LMArena, as published by 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 4.662 vs 60 category score; Arena WebDev 1547 vs 1539Medium
MathsClaude Sonnet 565 vs 63 category score; Arena Maths 1472 vs 1516Medium
ReasoningEither65 vs 65 category score; Arena Hard Prompts 1530 vs 1490Either
Images and other mediaClaude Opus 4.667 vs 61 category score; Arena Vision 1316 vs 1272Medium
Chat quality (human preference)Claude Opus 4.670 vs 65 on Arena votesMedium
Lowest costClaude Sonnet 5$4.00 vs $10.00 per 1M blended; agentic coding session $0.160 vs $0.400–
Fastest first answerClaude Opus 4.61.1 s (Claude Opus 4.6 (high)) vs 15.8 s (Claude Sonnet 5 (high)) 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 4.6 (high) leads on quality: 62.5 vs 59.0.
  • Claude Opus 4.6 (high) is stronger in coding, human preference, multimodal.
  • Claude Sonnet 5 (high) is stronger in maths, reasoning.
  • Claude Sonnet 5 (high) is 2.5× cheaper ($4.00 vs $10.00 per 1M blended).
  • Claude Sonnet 5 (high) streams 2.8× faster (99 vs 35 tokens per second).

At a glance

SpecClaude Opus 4.6Claude Sonnet 5
DeveloperAnthropicAnthropic
Released5 Feb 202630 Jun 2026
Context window (tokens)1,000,0001,000,000
Compared atClaude Opus 4.6 (high)Claude Sonnet 5 (high)
Open weightsNoNo
Price in / out / cached input per 1M$5.00 / $25.00 / $0.500$2.00 / $10.00 / $0.200

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 4.6 (high)Claude Sonnet 5 (high)Leader
Reasoning65.065.4level
Coding62.259.9Claude Opus 4.6
Agents & tools–52.9not comparable
Maths63.465.3Claude Sonnet 5
Human preference69.864.6Claude Opus 4.6
Multimodal66.760.9Claude Opus 4.6
Long context–62.9not 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 avg75ReasoningCodingMathsMultimodalHumanpreferenceClaude Opus 4.6, Reasoning: 65.0Claude Opus 4.6, Coding: 62.2Claude Opus 4.6, Maths: 63.4Claude Opus 4.6, Multimodal: 66.7Claude Opus 4.6, Human preference: 69.8Claude Sonnet 5, Reasoning: 65.4Claude Sonnet 5, Coding: 59.9Claude Sonnet 5, Maths: 65.3Claude Sonnet 5, Multimodal: 60.9Claude Sonnet 5, Human preference: 64.6

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

Model, click to add or removeIndex

Where sources disagree

Across the 12 benchmarks both have, Claude Opus 4.6 leads 12, Claude Sonnet 5 leads 0. Every overall index that rates both puts Claude Opus 4.6 ahead.

Overall indexClaude Opus 4.6 (high)Claude Sonnet 5 (high)Leader
BenchLeader Index62.559.0Claude Opus 4.6
Arena Text15031461Claude Opus 4.6

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 4.6 (high)Claude Sonnet 5 (high)
Blended price per 1M tokens$10.00$4.00
Input / output per 1M$5.00 / $25.00$2.00 / $10.00
Cached input per 1M$0.500$0.200
Price per task: chat reply$0.0095$0.0038
Price per task: summarize a 30-page report$0.075$0.030
Price per task: code edit$0.068$0.027
Price per task: agentic coding session$0.400$0.160
Price per task: structured extraction$0.015$0.0060
Agentic coding session, input mostly cached$0.198$0.079
Output speed35 tok/s99 tok/s
Time to first answer1.1 s15.8 s
Time to a complete answer, last measured 13 Nov 2026–40.7 s

Each model is compared at its best-ranked reasoning-effort setting. Claude Opus 4.6 (high) scores 62.5 and takes 1 s to its first answer token; Claude Opus 4.6 scores 62.1 in 1 s, Claude Opus 4.6 (no reasoning) scores 58.4 in 2 s. Claude Sonnet 5 (high) scores 59.0 and takes 16 s to its first answer token; Claude Sonnet 5 (max) scores 56.1 in 158 s, Claude Sonnet 5 (xhigh) scores 55.4 in 32 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

160 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 4.6 (high)Claude Sonnet 5 (high)
BenchLeader IndexBenchLeader62.559.0
Coding scoreBenchLeader62.259.9
Human preference scoreBenchLeader69.864.6
Maths scoreBenchLeader63.465.3
Multimodal scoreBenchLeader66.760.9
Reasoning scoreBenchLeader65.065.4
Agents & tools scoreBenchLeader–52.9
Long context scoreBenchLeader–62.9
Blended price $/MBenchLeader$10.00$4.00
Output speedBenchLeader35 tok/s99 tok/s
Time to first answerBenchLeader1.1 s15.8 s
Context windowBenchLeader1,000,000 tokens1,000,000 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub90.5%†80.3%†
Humanity's Last ExamScale AI / CAIS19.0%†–
SimpleBenchSimpleBench67.6%†60.6%†
Arena Hard PromptsArena (LMArena)15301490
LiveBench 1.0 ReasoningLiveBench88.7%88.7%†
GPQA Diamond (AA)Artificial Analysis84.0%†91.1%†
Humanity's Last Exam (AA)Artificial Analysis19.1%†35.7%
GPQA Diamond (Vals)Vals AI89.7%†88.9%†
Kagi LLM BenchmarkKagi LLM Benchmark72.4%†–
ARC-AGI-1ARC Prize94.0%–
ARC-AGI-2ARC Prize69.2%–
ARC-AGI-3ARC Prize0.5%†–
CritPtArtificial Analysis2.8%†15.1%
Arena ExpertArena (LMArena)15441509
Chess PuzzlesEpoch AI Benchmarking Hub21.0%†45.0%†
Mystery Game PuzzlesEpoch AI Benchmarking Hub15.0%†16.0%†
CL-benchEpoch AI Benchmarking Hub20.7%†–
CL-bench LifeEpoch AI Benchmarking Hub17.0%–
LMCAEpoch AI Benchmarking Hub55.8%†50.0%
DTBenchEpoch AI Benchmarking Hub91.2%†84.5%
ForecastBenchForecastBench63.1%†63.1%†
BTF-3Epoch AI Benchmarking Hub–14.2%†
Coding
SWE-bench Verified (Epoch)Epoch AI Benchmarking Hub78.7%†–
SciCodeSciCode–54.3%
WeirdMLWeirdML78.0%68.8%
Show all 160 benchmarks
MetricPublisherClaude Opus 4.6 (high)Claude Sonnet 5 (high)
Coding
FrontierCodeCognition26.6%†42.7%†
GSO-BenchGSO-Bench41.2%37.3%†
Arena CodingArena (LMArena)15471520
Arena WebDevArena (LMArena)15471539
LiveBench 1.0 CodingLiveBench78.2%80.7%†
LiveCodeBenchVals AI84.7%†82.4%†
IOIVals AI–45.0%†
SWE-bench (Vals)Vals AI78.2%†79.6%†
SWE-Bench ProScale AI SEAL51.9%†–
SWE-bench Verified (bash only)SWE-bench75.6%†–
SWE-bench Multilingual (bash only)SWE-bench72.0%†–
SWE-bench Verified (any scaffold)SWE-bench75.6%†–
Code MigrationVals AI–44.4%†
ProgramBenchVals AI–0.0%†
Vibe Code Bench 1-100Vals AI–13.8%†
Vibe Code Bench v1.1Vals AI57.6%†81.3%†
SWE-Bench Pro (private)Scale AI SEAL47.1%†–
SWE Atlas v1.0: Codebase QnAScale AI SEAL33.3%†–
SWE Atlas v1.0: RefactoringScale AI SEAL35.6%†–
SWE Atlas v1.0: Test WritingScale AI SEAL36.7%†–
SWE-Bench Pro V2Scale AI SEAL–93.2%†
SWE-Bench Pro V2 HARDScale AI SEAL–88.2%†
MirrorCodeEpoch AI Benchmarking Hub33.3%†63.3%†
Surface Evolver BenchEpoch AI Benchmarking Hub–60.0%†
DeepSWE v1.1Epoch AI Benchmarking Hub–48.2%
CursorBenchCursor–30.8%
ALE-BenchEpoch AI Benchmarking Hub996.5†1463.1
AlgoTuneAlgoTune1.5–
Terminal-Bench 4.0 (AA)Artificial Analysis–5.0%
Terminal-Bench 2.1 (AA)Artificial Analysis–80.5%†
Startrise FrontendStartrise–66.6%†
GameBench 2 OverallDuelLab GameBench 2–46.6†
GameBench 2 by reasoning settingDuelLab GameBench 2–54.4†
Design Arena WebsiteDesign Arena1283†1268†
FrontierCode 2.0 (AA)Artificial Analysis–17.8%†
Agents & tools
Terminal-BenchTerminal-Bench79.8%†12.1%†
CybenchCybench93.0%†–
Remote Labor IndexScale AI / CAIS4.2%†–
APEX-AgentsMercor46.3%†54.5%†
Arena AgentArena (LMArena)–2
LiveBench Agentic CodingLiveBench49.0%59.4%†
Terminal-Bench HardArtificial Analysis48.5%†–
τ²-Bench Telecom (AA)Artificial Analysis84.8%†–
Terminal-Bench 2.1 (Vals)Vals AI–74.5%†
MCP AtlasScale AI SEAL76.8%†–
HiL-BenchScale AI SEAL38.3%†–
τ³-bench Bankingτ²-bench27.3%†–
GDPval-AA v2.1Artificial Analysis–1262
τ³-Banking (AA)Artificial Analysis–37.3%†
Analyst Agent (AA)Artificial Analysis–46.3%†
APEX-Agents (AA)Artificial Analysis33.0%†–
CyberBenchVals AI–61.9%†
Finance Agent v2Vals AI–53.9%†
Harvey's Legal Agent Benchmark v1Vals AI–5.0%†
Legal Research BenchVals AI–41.8%†
SkillsBenchVals AI–46.5%†
SREBenchVals AI–0.4%†
Tax Agent BenchVals AI–29.4%†
Terminal-Bench 2.0 (Vals)Vals AI58.4%†–
Terminal-Bench 4.0 (Vals)Vals AI–10.6%†
Terminal-Bench ScienceVals AI–5.7%†
Arena SearchArena (LMArena)1222†1191†
Arena Agent Task CompletionArena (LMArena)–-0.6
DeepResearch BenchDeepResearch Bench55.3%–
METR Time HorizonsMETR78.9%†–
GBAEvalEpoch AI Benchmarking Hub44.1%†65.3%†
Vending-Bench 2Andon Labs8017.6†6377.7†
AutomationBenchArtificial Analysis–32.1%
GDP.pdf (AA)Artificial Analysis–9.4%
EnterpriseOps-GymArtificial Analysis–44.7%†
AA-Briefcase v1.1Artificial Analysis–1177
Design Arena AgenticDesign Arena1196†1222†
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub66.0%†65.6%†
FrontierMath Tier 4Epoch AI Benchmarking Hub26.8%†29.3%†
OTIS Mock AIMEEpoch AI Benchmarking Hub94.4%†80.0%†
ProofBenchVals AI50.0%†77.0%†
LiveBench MathematicsLiveBench89.3%92.9%†
AIME (Vals)Vals AI95.6%†–
AIME 2026MathArena96.7%–
HMMT February 2026MathArena96.2%–
USAMO 2026MathArena47.0%–
MathArena ApexMathArena34.5%–
Arena MathsArena (LMArena)15161472
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub47.0%†33.7%†
LiveBench 1.0 Data AnalysisLiveBench69.9%71.7%†
MMLU-ProVals AI89.1%†87.5%†
LegalBenchVals AI85.3%†83.9%†
CorpFinVals AI67.0%†67.0%†
TaxEvalVals AI76.0%†75.6%†
MedQAVals AI95.4%†–
PRBench FinanceScale AI SEAL53.3%†–
PRBench LegalScale AI SEAL52.3%†–
MultiNRCScale AI SEAL48.3%†–
CaseLaw v2Vals AI62.1%†–
Excel Modeling BenchmarkVals AI–66.3%†
MedCodeVals AI49.1%†47.5%†
MedScribeVals AI86.7%†76.0%†
Public Benefits Bench v1.1Vals AI–66.0%†
DrugDiscoveryBenchScale AI SEAL27.7%†50.0%†
EBR-benchEpoch AI Benchmarking Hub12.7%†–
Global-MMLU-Lite (AA)Artificial Analysis90.6%†–
FACTS ParametricGoogle–20.5%†
Instruction following
LiveBench LanguageLiveBench83.3%75.0%†
LiveBench Instruction FollowingLiveBench63.3%63.9%†
IFBenchArtificial Analysis44.6%†–
MultiChallengeScale AI SEAL56.0%†–
TutorBenchScale AI SEAL53.5%†–
Arena Instruction FollowingArena (LMArena)15111467
Human preference
Arena TextArena (LMArena)15031461
EQ-Bench 4EQ-Bench1210†1221†
EQ-Bench Creative Writing v3EQ-Bench1810†1798†
Arena Creative WritingArena (LMArena)14991434
Arena Multi-turnArena (LMArena)15171473
Arena Longer QueriesArena (LMArena)15221481
Multimodal
Arena VisionArena (LMArena)13161272
MMMU-ProArtificial Analysis72.5%†77.3%†
VISTAScale AI SEAL45.5%†–
MMMU-Pro (Vals)Vals AI83.9%†83.0%†
MortgageTaxVals AI68.5%†70.0%†
Humanity's Sixth SenseScale AI SEAL–24.8%†
VTBScale AI SEAL27.5%†–
GeoBenchGeoBench–74.0%
Blueprint-Bench 2Epoch AI Benchmarking Hub–24.9%†
Furniture AssemblyEpoch AI Benchmarking Hub28.3%†–
Long context
AA-LCR v1.1Artificial Analysis67.0%†76.7%
Arena DocumentArena (LMArena)14971469
MLCRArtificial Analysis–4.4%
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub156.3†156.9†
LiveBench 1.0LiveBench74.5%76.0%†
AA Intelligence Index v4.3.2Artificial Analysis26.4†31.7
AA Progress Index v1Artificial Analysis274.5†296.8
Vals Multimodal IndexVals AI–68.8%†
Safety & honesty
FORTRESSScale AI SEAL20.5%†–
MASKScale AI SEAL96.3%†–
DistressBenchScale AI SEAL–68.0%†

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 Sonnet 5 (high): 2 new results (GDPval-AA v2.1, AA-Briefcase v1.1).
  • Claude Opus 4.6 (high): BenchLeader Index 63.0 → 62.5.
  • Claude Sonnet 5 (high): BenchLeader Index 59.5 → 59.0.
  • Claude Sonnet 5 (high): 1 new result (GeoBench).
  • Claude Sonnet 5 (high): 1 score revision.
  • Claude Sonnet 5 (high): 1 score revision.
  • Claude Sonnet 5 (high): 1 new result (AA Progress Index v1).
  • Claude Sonnet 5 (high): BenchLeader Index 60.0 → 59.5.
  • Claude Sonnet 5 (high): 1 new result (MLCR).
  • Claude Sonnet 5 (high): 1 score revision.

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

Claude Opus 4.6 vs Claude Sonnet 5: questions

Is Claude Opus 4.6 better than Claude Sonnet 5?
Claude Opus 4.6 (high) leads on quality: 62.5 vs 59.0. The BenchLeader Index combines every independent quality benchmark; Claude Opus 4.6 (high) is ahead overall as of 16 Nov 2026, but check the category scores for your use.
Claude Opus 4.6 vs Claude Sonnet 5: which is cheaper, and will that change?
Claude Sonnet 5 is cheaper today: $4.00 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 4.6 or Claude Sonnet 5 better for coding?
Claude Opus 4.6 scores higher in coding (62 vs 60 on the category index, where 50 is average). On Arena WebDev, the top shared coding benchmark, it is 1547 for Claude Opus 4.6 against 1539 for Claude Sonnet 5.
Which is faster, Claude Opus 4.6 or Claude Sonnet 5?
Claude Sonnet 5 streams ~2× faster (99 vs 35 output tokens per second, Artificial Analysis 7-day median).
Which is better for long documents?
Both accept 1,000,000 tokens of context.
More questions (3)
Which has lower latency?
Claude Opus 4.6 answers first: 1.1 s against 15.8 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 4.6 vs Claude Sonnet 5?
Across the 12 benchmarks both have, Claude Opus 4.6 leads 12, Claude Sonnet 5 leads 0. Every overall index that rates both puts Claude Opus 4.6 ahead.
When was Claude Sonnet 5 released?
Claude Sonnet 5 was released on 30 Jun 2026.