BenchLeader
Menu
Best LLMsChoose a modelCoding plansLeaderboardsModelsBenchmarksProvidersReleases12

Claude Opus 4.5 vs Claude Opus 5.5

Full profiles: Claude Opus 4.5 (Anthropic) and Claude Opus 5.5 (Anthropic): every benchmark, price and rank.

Updated · Data from 14 sources

As of 9 Nov 2026, Claude Opus 5.5 is ahead of Claude Opus 4.5 on quality (68.9 vs 59.7 on the BenchLeader Index), and Claude Opus 5.5 is 1.3× cheaper at $8.00 vs $10.00 per 1M tokens blended. Choose Opus 4.5 for agents & tools (75 vs 63) and fast first answers (12.6 s vs 380.6 s); choose Opus 5.5 for coding (80 vs 61), knowledge (74 vs 58), and reasoning (72 vs 57), where it also streams ~1.5× faster.

Key facts (as of 9 Nov 2026)

  • Claude Opus 4.5 scores 59.7 on the BenchLeader Index and Claude Opus 5.5 scores 68.9 (BenchLeader, 9 Nov 2026).
  • Claude Opus 4.5 costs $10.00 per 1M tokens blended (list price, 9 Nov 2026).
  • Claude Opus 5.5 costs $8.00 per 1M tokens blended (list price, 9 Nov 2026).
  • Claude Opus 5.5 streams ~1.5× faster than Claude Opus 4.5 (Artificial Analysis, 7-day median, 9 Nov 2026).
  • Of the 8 benchmarks both models have, Claude Opus 5.5 leads 7 (BenchLeader, 9 Nov 2026).
Claude Opus 4.5 benchmarks thinking Anthropic Claude Opus 5.5 benchmarks max AnthropicAdd a third model

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 5.580 vs 61 category scoreHigh
Agents & tool useClaude Opus 4.575 vs 63 category scoreHigh
MathsClaude Opus 5.574 vs 64 category scoreHigh
ReasoningClaude Opus 5.572 vs 57 category score; ARC-AGI-2 91.7% vs 37.6%High
KnowledgeClaude Opus 5.574 vs 58 category scoreHigh
Long documentsClaude Opus 5.567 vs 63 category score; AA-LCR v1.1 84.7% vs 77.3%Medium
Images and other mediaClaude Opus 5.570 vs 57 category score; MMMU-Pro 87.7% vs 74.0%High
Lowest costClaude Opus 5.5$8.00 vs $10.00 per 1M blended; agentic coding session $0.320 vs $0.400–
Fastest first answerClaude Opus 4.512.6 s (Claude Opus 4.5 (thinking)) vs 380.6 s (Claude Opus 5.5 (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 5.5 (max) leads on quality: 68.9 vs 59.7.
  • Claude Opus 4.5 (thinking) is stronger in agents & tools, instruction following.
  • Claude Opus 5.5 (max) is stronger in coding, knowledge, long context, maths, multimodal, reasoning.
  • Claude Opus 5.5 (max) is 1.3× cheaper ($8.00 vs $10.00 per 1M blended).
  • Claude Opus 5.5 (max) streams 1.7× faster (115 vs 67 tokens per second).

At a glance

SpecClaude Opus 4.5Claude Opus 5.5
DeveloperAnthropicAnthropic
Released24 Nov 202522 Sep 2026
Context window (tokens)200,0001,000,000
Max output (tokens)–128,000 (up to 300K on the Message Batches API (beta))
Input types–text, image
Reasoning effort settings–low, medium, high, xhigh, max
Compared atClaude Opus 4.5 (thinking)Claude Opus 5.5 (max)
Open weightsNoNo
Price in / out / cached input per 1M$5.00 / $25.00 / $0.500$4.00 / $20.00 / $0.200
API model ID–claude-opus-5-5
Where to use it–Claude API, Amazon Bedrock, Google Cloud, Microsoft Foundry

Limits, availability and announced prices from the vendors' own pages: platform.claude.com (checked 20 Oct 2026). Everything else is from the day's data.

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 4.5 (thinking)Claude Opus 5.5 (max)Leader
Reasoning57.172.3Claude Opus 5.5
Coding60.680.4Claude Opus 5.5
Agents & tools74.862.7Claude Opus 4.5
Maths64.274.0Claude Opus 5.5
Knowledge58.373.7Claude Opus 5.5
Instruction following53.2–not comparable
Multimodal57.070.3Claude Opus 5.5
Long context63.367.1Claude Opus 5.5

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 & toolsMathsKnowledgeLong contextMultimodalClaude Opus 4.5, Reasoning: 57.1Claude Opus 4.5, Coding: 60.6Claude Opus 4.5, Agents & tools: 74.8Claude Opus 4.5, Maths: 64.2Claude Opus 4.5, Knowledge: 58.3Claude Opus 4.5, Long context: 63.3Claude Opus 4.5, Multimodal: 57.0Claude Opus 5.5, Reasoning: 72.3Claude Opus 5.5, Coding: 80.4Claude Opus 5.5, Agents & tools: 62.7Claude Opus 5.5, Maths: 74.0Claude Opus 5.5, Knowledge: 73.7Claude Opus 5.5, Long context: 67.1Claude Opus 5.5, Multimodal: 70.3

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

ModelIndex

Where sources disagree

Across the 8 benchmarks both have, Claude Opus 4.5 leads 1, Claude Opus 5.5 leads 7. Every overall index that rates both puts Claude Opus 5.5 ahead.

Overall indexClaude Opus 4.5 (thinking)Claude Opus 5.5 (max)Leader
BenchLeader Index59.768.9Claude Opus 5.5
Arena Text1474†1506Claude Opus 5.5

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

MeasureClaude Opus 4.5 (thinking)Claude Opus 5.5 (max)
Blended price per 1M tokens$10.00$8.00
Input / output per 1M$5.00 / $25.00$4.00 / $20.00
Cached input per 1M$0.500$0.200
Price per task: chat reply$0.0095$0.0076
Price per task: summarize a 30-page report$0.075$0.060
Price per task: code edit$0.068$0.054
Price per task: agentic coding session$0.400$0.320
Price per task: structured extraction$0.015$0.012
Agentic coding session, input mostly cached$0.198$0.149
Cost per benchmark task (AA Index)–$10.04
Output tokens per task (AA Index)–173k
Of which reasoning–120k
Time per task (AA Index)–25 min
Output speed67 tok/s115 tok/s
Time to first answer12.6 s380.6 s
Time to a complete answer65.0 s771.1 s

Each model is compared at its best-ranked reasoning-effort setting. Claude Opus 4.5 (thinking) scores 59.7 and takes 13 s to its first answer token; Claude Opus 4.5 (high) scores 59.0 in 1 s, Claude Opus 4.5 scores 57.9 in 1 s. Claude Opus 5.5 (max) scores 68.9 and takes 381 s to its first answer token; Claude Opus 5.5 (xhigh) scores 65.5 in 84 s, Claude Opus 5.5 (high) scores 65.4 in 28 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

189 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 4.5 (thinking)Claude Opus 5.5 (max)
BenchLeader IndexBenchLeader59.768.9
Agents & tools scoreBenchLeader74.862.7
Coding scoreBenchLeader60.680.4
Instruction following scoreBenchLeader53.2–
Knowledge scoreBenchLeader58.373.7
Long context scoreBenchLeader63.367.1
Maths scoreBenchLeader64.274.0
Multimodal scoreBenchLeader57.070.3
Reasoning scoreBenchLeader57.172.3
Blended price $/MBenchLeader$10.00$8.00
Output speedBenchLeader67 tok/s115 tok/s
Time to first answerBenchLeader12.6 s380.6 s
Context windowBenchLeader200,000 tokens1,000,000 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub86.0%†90.6%
Humanity's Last ExamScale AI / CAIS25.2%†–
SimpleBenchSimpleBench62.0%†–
Arena Hard PromptsArena (LMArena)1498†1530†
LiveBench 2.0 ReasoningLiveBench–92.2%†
LiveBench 1.0 ReasoningLiveBench80.1%†92.2%
GPQA Diamond (AA)Artificial Analysis86.6%–
Humanity's Last Exam (AA)Artificial Analysis30.1%61.4%
HLE-Diamond (AA)Artificial Analysis–67.9%
GPQA Diamond (Vals)Vals AI85.9%–
Kagi LLM BenchmarkKagi LLM Benchmark80.2%–
ARC-AGI-1ARC Prize80.0%97.5%
ARC-AGI-2ARC Prize37.6%91.7%
CritPtArtificial Analysis4.6%31.7%
CritPt v2 hard subset (AA)Artificial Analysis–68.0%
MysteryMechanismVals AI–49.5%†
SciPredictScale AI SEAL23.1%†–
Chess PuzzlesEpoch AI Benchmarking Hub14.0%†67.0%
Mystery Game PuzzlesEpoch AI Benchmarking Hub22.0%†71.0%
CL-benchEpoch AI Benchmarking Hub21.1%†–
LMCAEpoch AI Benchmarking Hub44.5%†68.2%
DTBenchEpoch AI Benchmarking Hub89.9%†98.9%
ForecastBenchForecastBench64.9%†–
Coding
SWE-bench Verified (Epoch)Epoch AI Benchmarking Hub76.7%†–
SciCodeSciCode–66.9%
Show all 189 benchmarks
MetricPublisherClaude Opus 4.5 (thinking)Claude Opus 5.5 (max)
Coding
WeirdMLWeirdML63.7%†–
FrontierCodeCognition–54.6%†
GSO-BenchGSO-Bench26.5%†–
Arena CodingArena (LMArena)1523†1546†
Arena WebDevArena (LMArena)1469†1818
LiveBench 2.0 CodingLiveBench–87.1%†
LiveBench 1.0 CodingLiveBench79.7%†89.3%
LiveCodeBenchVals AI83.7%–
IOIVals AI–95.1%†
SWE-bench (Vals)Vals AI76.4%–
SWE-Bench ProScale AI SEAL45.9%†–
SWE-bench Verified (bash only)SWE-bench76.8%†–
SWE-bench Verified (any scaffold)SWE-bench79.2%†–
Code MigrationVals AI–66.7%†
Code Migration v1.1Vals AI–81.0%†
ProgramBenchVals AI–18.5%†
SWE-bench MultimodalVals AI–70.2%†
Vibe Code Bench 1-100Vals AI–30.4%†
Vibe Code Bench v1.1Vals AI20.6%90.3%†
SWE-Bench Pro (private)Scale AI SEAL45.9%†–
MirrorCodeEpoch AI Benchmarking Hub–78.9%†
CursorBenchCursor–57.8%
ALE-BenchEpoch AI Benchmarking Hub1025.4†2147.4†
AlgoTuneAlgoTune1.8†–
FrontierSWEEpoch AI Benchmarking Hub–62.3%
Terminal-Bench 4.0 (AA)Artificial Analysis–59.6%
Startrise FrontendStartrise–71.1%†
GameBench 2 OverallDuelLab GameBench 247.0†87.6†
GameBench 2 by reasoning settingDuelLab GameBench 2–94.8†
Design Arena WebsiteDesign Arena1244†1325†
FrontierCode 1.1 (AA)Artificial Analysis–52.2%
FrontierCode 2.0 (AA)Artificial Analysis–46.4%
LiveCodeBench (AA)Artificial Analysis87.1%–
Agents & tools
Terminal-BenchTerminal-Bench63.1%†65.8%
GDPvalOpenAI45.5%†–
CybenchCybench82.0%†–
Remote Labor IndexScale AI / CAIS3.8%†21.3%†
APEX-AgentsMercor–73.5%
Arena AgentArena (LMArena)–20
LiveBench Long AgenticLiveBench–72.8%†
LiveBench BrowserLiveBench–88.4%†
LiveBench Agentic CodingLiveBench39.7%†71.7%
Terminal-Bench HardArtificial Analysis47.0%–
τ²-Bench Telecom (AA)Artificial Analysis89.5%–
Terminal-Bench 2.1 (Vals)Vals AI–87.6%†
MCP AtlasScale AI SEAL69.8%†85.4%†
HiL-BenchScale AI SEAL–59.0%†
BFCL OverallBerkeley Function Calling Leaderboard77.5%†–
τ²-benchτ²-bench85.3%†–
τ³-bench Bankingτ²-bench24.7%†–
GDPval-AA v2.1, normalised scoreArtificial Analysis–68.3%
GDPval-AA v2.1Artificial Analysis–1866
ITBench SRE (AA)Artificial Analysis–38.2%
Analyst Agent (AA)Artificial Analysis–56.3%
CUA-benchVals AI–14.0%
CyberBenchVals AI–55.4%†
Finance Agent v2Vals AI–58.6%†
Finance Agent v2.1Vals AI–67.8%†
Harvey's Legal Agent Benchmark v1.1Vals AI–9.2%†
Harvey's Legal Agent Benchmark v1Vals AI–3.8%†
Legal Research BenchVals AI–50.5%†
Poker AgentVals AI1033.4%†–
Robo-benchVals AI–14.6%
SREBenchVals AI–33.6%†
Tax Agent BenchVals AI–44.5%†
Terminal-Bench 2.0 (Vals)Vals AI53.9%–
Terminal-Bench 4.0 (Vals)Vals AI–65.2%†
Terminal-Bench ScienceVals AI–47.1%†
Time Horizon Index: KSPVals AI–91.3%†
Arena SearchArena (LMArena)1186†1214†
BALROGBALROG43.0%†–
DeepResearch BenchDeepResearch Bench54.8%†–
METR Time HorizonsMETR75.0%†–
Vending-Bench 2Andon Labs4967.1†9235.3†
AutomationBenchArtificial Analysis–69.5%
GDP.pdf (AA)Artificial Analysis–26.2%
Harvey LAB-AA v1.1Harvey–4.2%
AA-Briefcase v1.1Artificial Analysis–1800
GDPxGDPx by SemiAnalysis–12.0%
Design Arena AgenticDesign Arena1151†1334†
Terminal-Bench-Science 0.1 (AA)Artificial Analysis–59.0%
CWE-Bench (AA)Artificial Analysis–58.3%
DeepSec-Bench (AA)Artificial Analysis–26.9%
CyberGym end-to-end (AA)Artificial Analysis–0.8%
DeepSearchQAGoogle24.0%–
FACTS SearchGoogle–88.4%†
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub34.4%†91.2%
FrontierMath Tier 4Epoch AI Benchmarking Hub4.9%†95.0%
OTIS Mock AIMEEpoch AI Benchmarking Hub86.1%†100.0%
ProofBenchVals AI36.0%†100.0%
LiveBench MathematicsLiveBench90.4%†97.1%
AIME (Vals)Vals AI95.4%–
MGSMVals AI95.2%–
Arena MathsArena (LMArena)1463†1518†
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub45.7%†72.2%
LiveBench 2.0 Data AnalysisLiveBench–80.3%†
LiveBench ResearchLiveBench–88.9%†
LiveBench 1.0 Data AnalysisLiveBench74.4%†80.3%
AA-Omniscience v1.1Artificial Analysis–48.1
MMLU-ProVals AI87.3%–
LegalBenchVals AI84.6%–
CorpFinVals AI65.1%–
TaxEvalVals AI74.9%–
MedQAVals AI95.9%–
PRBench FinanceScale AI SEAL46.2%–
PRBench LegalScale AI SEAL44.2%47.6%†
MultiNRCScale AI SEAL48.6%–
BioMysteryBenchVals AI–79.3%†
CaseLaw v2Vals AI62.6%–
ClaimBenchVals AI–100.0%†
Excel Modeling BenchmarkVals AI–75.9%†
Excel Modeling Benchmark v1.1Vals AI–75.8%†
MedCodeVals AI49.2%49.8%†
MedScribeVals AI85.3%91.4%†
Public Benefits Bench v1.1Vals AI–70.6%†
EBR-benchEpoch AI Benchmarking Hub14.3%†71.4%
GDP.pdfEpoch AI Benchmarking Hub–30.6%
AA-Omniscience v1.1: accuracyArtificial Analysis–65.5%
AA-Omniscience v1.1: non-hallucinationArtificial Analysis–49.7%
Global-MMLU-Lite (AA)Artificial Analysis91.3%–
HealthBench Professional (AA)OpenAI–59.9%
Instruction following
LiveBench LanguageLiveBench81.3%†86.3%
LiveBench Instruction FollowingLiveBench62.5%†65.7%
IFBenchArtificial Analysis58.0%–
MultiChallengeScale AI SEAL59.0%–
TutorBenchScale AI SEAL51.2%–
Arena Instruction FollowingArena (LMArena)1474†1519†
Human preference
Arena TextArena (LMArena)1470†1506†
EQ-Bench 4EQ-Bench–1340†
Arena Creative WritingArena (LMArena)1461†1517†
Arena Multi-turnArena (LMArena)1484†1500†
Arena Longer QueriesArena (LMArena)1492†1520†
Multimodal
Arena VisionArena (LMArena)–1324†
LiveBench DesignLiveBench–83.3%†
MMMU-ProArtificial Analysis74.0%87.7%
VISTAScale AI SEAL46.4%–
MMMU (validation)MMMU80.7%†–
MMMU-Pro (official)MMMU73.9%†–
MMMU-Pro (Vals)Vals AI83.0%–
MortgageTaxVals AI67.7%–
SAGEVals AI–91.3%†
GeoBenchGeoBench75.0%†–
VPCTEpoch AI Benchmarking Hub40.0%†–
Blueprint-Bench 2Epoch AI Benchmarking Hub–51.2%†
Code2Video-AAArtificial Analysis–1536
AA-3DArtificial Analysis–1202
Long context
AA-LCR v1.1Artificial Analysis77.3%84.7%
Arena DocumentArena (LMArena)1468†–
MLCRArtificial Analysis–27.8%
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub151.8†168.4†
LiveBench 2.0LiveBench–83.4%†
LiveBench 1.0LiveBench72.6%†83.2%
AA Intelligence Index v5.0Artificial Analysis–59.1
AA Intelligence Index v4.3.2Artificial Analysis29.157.6
AA Progress Index v1Artificial Analysis284.4350
Vals IndexVals AI–70.1†
Vals Finance IndexVals AI–65.3%†
Vals RSI IndexVals AI14.8%†37.3%
Vals Science IndexVals AI–58.6%†
Vals Router IndexVals AI–64.2%†
AA Cyber IndexArtificial Analysis–28.7
Safety & honesty
FORTRESSScale AI SEAL9.6%5.8%
MASKScale AI SEAL92.5%–
Metadata
AA Openness IndexArtificial Analysis11.1–

Data as of 2026-11-09. 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

  • Claude Opus 5.5 (max): 2 score revisions.
  • Claude Opus 5.5 (max): 1 score revision.
  • Claude Opus 5.5 (max): 1 score revision.
  • Claude Opus 5.5 (max): 2 score revisions.
  • Claude Opus 5.5 (max): 2 score revisions.
  • Claude Opus 5.5 (max): 1 score revision.
  • Claude Opus 4.5 (thinking): BenchLeader Index 60.1 → 59.6.
  • Claude Opus 4.5 (thinking): 1 new result (AA Progress Index v1).
  • Claude Opus 5.5 (max): 5 new results (AA Intelligence Index v5.0, AA Progress Index v1, HLE-Diamond (AA)…); 3 score revisions; cost per task moved from $5.98/M to $10.04/M (68% up).
  • Claude Opus 4.5 (thinking): 1 new result (Global-MMLU-Lite (AA)).

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

Claude Opus 4.5 vs Claude Opus 5.5: questions

Is Claude Opus 5.5 better than Claude Opus 4.5?
Claude Opus 5.5 (max) leads on quality: 68.9 vs 59.7. The BenchLeader Index combines every independent quality benchmark; Claude Opus 5.5 (max) is ahead overall as of 9 Nov 2026, but check the category scores for your use.
Claude Opus 4.5 vs Claude Opus 5.5: which is cheaper, and will that change?
Claude Opus 5.5 is cheaper today: $8.00 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 4.5 or Claude Opus 5.5 better for coding?
Claude Opus 5.5 scores higher in coding (80 vs 61 on the category index, where 50 is average).
Which is faster, Claude Opus 4.5 or Claude Opus 5.5?
Claude Opus 5.5 streams ~1.5× faster (115 vs 67 output tokens per second, Artificial Analysis 7-day median).
Is Claude Opus 4.5 or Claude Opus 5.5 better for agents and tool use?
Claude Opus 4.5 scores higher in agentic tasks (75 vs 63 on the category index, where 50 is average).
More questions (4)
Which is better for long documents?
Claude Opus 5.5 scores higher on long-context benchmarks (67 vs 63). Claude Opus 5.5 accepts more context: 1,000,000 against 200,000 tokens for Claude Opus 4.5.
Which has lower latency?
Claude Opus 4.5 answers first: 12.6 s against 380.6 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 4.5 vs Claude Opus 5.5?
Across the 8 benchmarks both have, Claude Opus 4.5 leads 1, Claude Opus 5.5 leads 7. Every overall index that rates both puts Claude Opus 5.5 ahead.
When was Claude Opus 5.5 released?
Claude Opus 5.5 was released on 22 Sep 2026.