BenchLeader
Menu
Best LLMsChoose a modelCoding plansLeaderboardsModelsBenchmarksProvidersReleases12

Claude Opus 5.5 vs o3

Full profiles: Claude Opus 5.5 (Anthropic) and o3 (OpenAI): every benchmark, price and rank.

Updated · Data from 21 sources

As of 9 Nov 2026, Claude Opus 5.5 is ahead of o3 on quality (68.9 vs 61.0 on the BenchLeader Index), but o3 is 2.3× cheaper at $3.50 vs $8.00 per 1M tokens blended. Choose Claude Opus 5.5 for coding (80 vs 62), knowledge (74 vs 57), and multimodal (70 vs 57); choose o3 for fast first answers (5.3 s vs 380.6 s) and agents & tools (70 vs 63).

Key facts (as of 9 Nov 2026)

  • Claude Opus 5.5 scores 68.9 on the BenchLeader Index and o3 scores 61.0 (BenchLeader, 9 Nov 2026).
  • Claude Opus 5.5 costs $8.00 per 1M tokens blended (list price, 9 Nov 2026).
  • o3 costs $3.50 per 1M tokens blended (list price, 9 Nov 2026).
  • Of the 6 benchmarks both models have, Claude Opus 5.5 leads 5 (BenchLeader, 9 Nov 2026).
Claude Opus 5.5 benchmarks max Anthropic o3 benchmarks OpenAIAdd 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 62 category scoreHigh
Agents & tool useo370 vs 63 category scoreHigh
MathsClaude Opus 5.574 vs 71 category scoreMedium
ReasoningClaude Opus 5.572 vs 61 category score; Humanity's Last Exam (AA) 61.4% vs 20.1%High
KnowledgeClaude Opus 5.574 vs 57 category scoreHigh
Long documentsClaude Opus 5.567 vs 62 category score; AA-LCR v1.1 84.7% vs 74.7%Medium
Images and other mediaClaude Opus 5.570 vs 57 category score; MMMU-Pro 87.7% vs 70.1%High
Chat quality (human preference)–Only o3 has an Arena rating (61 category score)Not comparable
Lowest costo3$3.50 vs $8.00 per 1M blended; agentic coding session $0.152 vs $0.320–
Fastest first answero35.3 s (o3) 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 61.0.
  • Claude Opus 5.5 (max) is stronger in coding, knowledge, long context, maths, multimodal, reasoning.
  • o3 is stronger in agents & tools, human preference, instruction following.
  • o3 is 2.3× cheaper ($3.50 vs $8.00 per 1M blended).

At a glance

SpecClaude Opus 5.5o3
DeveloperAnthropicOpenAI
Released22 Sep 202616 Apr 2025
Context window (tokens)1,000,000200,000
Max output (tokens)128,000 (up to 300K on the Message Batches API (beta))–
Input typestext, image–
Reasoning effort settingslow, medium, high, xhigh, max–
Compared atClaude Opus 5.5 (max)o3
Open weightsNoNo
Price in / out / cached input per 1M$4.00 / $20.00 / $0.200$2.00 / $8.00 / $0.500
API model IDclaude-opus-5-5–
Where to use itClaude 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 5.5 (max)o3Leader
Reasoning72.360.9Claude Opus 5.5
Coding80.461.5Claude Opus 5.5
Agents & tools62.770.3o3
Maths74.070.6Claude Opus 5.5
Knowledge73.756.5Claude Opus 5.5
Instruction following–65.2not comparable
Human preference–61.1not comparable
Multimodal70.356.6Claude Opus 5.5
Long context67.161.9Claude 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 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: 70.3o3, Reasoning: 60.9o3, Coding: 61.5o3, Agents & tools: 70.3o3, Maths: 70.6o3, Knowledge: 56.5o3, Long context: 61.9o3, Multimodal: 56.6

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

ModelIndex

Where sources disagree

Across the 6 benchmarks both have, Claude Opus 5.5 leads 5, o3 leads 1. Every overall index that rates both puts Claude Opus 5.5 ahead.

Overall indexClaude Opus 5.5 (max)o3Leader
BenchLeader Index68.961.0Claude Opus 5.5
Arena Text1506†1432Claude 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 5.5 (max)o3
Blended price per 1M tokens$8.00$3.50
Input / output per 1M$4.00 / $20.00$2.00 / $8.00
Cached input per 1M$0.200$0.500
Price per task: chat reply$0.0076$0.0032
Price per task: summarize a 30-page report$0.060$0.029
Price per task: code edit$0.054$0.024
Price per task: agentic coding session$0.320$0.152
Price per task: structured extraction$0.012$0.0056
Agentic coding session, input mostly cached$0.149$0.085
Cost per benchmark task (AA Index)$10.04–
Output tokens per task (AA Index)173k–
Of which reasoning120k–
Time per task (AA Index)25 min–
Output speed115 tok/s112 tok/s
Time to first answer380.6 s5.3 s
Time to a complete answer771.1 s16.7 s

Each model is compared at its best-ranked reasoning-effort setting. 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. o3 scores 61.0 and takes 5 s to its first answer token; o3 (high) scores 53.9 in 5 s, o3 (medium) scores 53.3 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

191 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 5.5 (max)o3
BenchLeader IndexBenchLeader68.961.0
Agents & tools scoreBenchLeader62.770.3
Coding scoreBenchLeader80.461.5
Knowledge scoreBenchLeader73.756.5
Long context scoreBenchLeader67.161.9
Maths scoreBenchLeader74.070.6
Multimodal scoreBenchLeader70.356.6
Reasoning scoreBenchLeader72.360.9
Human preference scoreBenchLeader–61.1
Instruction following scoreBenchLeader–65.2
Blended price $/MBenchLeader$8.00$3.50
Output speedBenchLeader115 tok/s112 tok/s
Time to first answerBenchLeader380.6 s5.3 s
Context windowBenchLeader1,000,000 tokens200,000 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub90.6%81.8%†
Humanity's Last ExamScale AI / CAIS–20.3%†
SimpleBenchSimpleBench–53.1%†
Arena Hard PromptsArena (LMArena)1530†1441
LiveBench 2.0 ReasoningLiveBench92.2%†–
LiveBench 1.0 ReasoningLiveBench92.2%–
GPQA Diamond (AA)Artificial Analysis–82.7%
Humanity's Last Exam (AA)Artificial Analysis61.4%20.1%
HLE-Diamond (AA)Artificial Analysis67.9%–
GPQA Diamond (Vals)Vals AI–84.1%†
Kagi LLM BenchmarkKagi LLM Benchmark–67.6%
GPQA Diamond (HELM)HELM Capabilities–75.3%
ARC-AGI-1ARC Prize97.5%60.8%†
ARC-AGI-2ARC Prize91.7%6.5%†
CritPtArtificial Analysis31.7%1.1%
CritPt v2 hard subset (AA)Artificial Analysis68.0%–
MysteryMechanismVals AI49.5%†–
SciPredictScale AI SEAL–17.9%
Chess PuzzlesEpoch AI Benchmarking Hub67.0%36.0%†
Mystery Game PuzzlesEpoch AI Benchmarking Hub71.0%29.0%†
CL-benchEpoch AI Benchmarking Hub–17.8%†
LMCAEpoch AI Benchmarking Hub68.2%39.7%†
DTBenchEpoch AI Benchmarking Hub98.9%84.8%†
ForecastBenchForecastBench–64.6%
Coding
SWE-bench Verified (Epoch)Epoch AI Benchmarking Hub–62.3%†
Show all 191 benchmarks
MetricPublisherClaude Opus 5.5 (max)o3
Coding
SciCodeSciCode66.9%–
WeirdMLWeirdML–52.4%†
FrontierCodeCognition54.6%†–
GSO-BenchGSO-Bench–8.8%†
Arena CodingArena (LMArena)1546†1460
Arena WebDevArena (LMArena)1818–
LiveBench 2.0 CodingLiveBench87.1%†–
LiveBench 1.0 CodingLiveBench89.3%–
LiveCodeBenchVals AI–83.9%†
IOIVals AI95.1%†–
Aider PolyglotAider polyglot leaderboard–81.3%
SWE-bench Verified (bash only)SWE-bench–58.4%
SWE-bench Verified (any scaffold)SWE-bench–58.4%
Code MigrationVals AI66.7%†–
Code Migration v1.1Vals AI81.0%†–
ProgramBenchVals AI18.5%†–
SWE-bench MultimodalVals AI70.2%†–
Vibe Code Bench 1-100Vals AI30.4%†–
Vibe Code Bench v1.1Vals AI90.3%†–
MirrorCodeEpoch AI Benchmarking Hub78.9%†–
CadEvalEpoch AI Benchmarking Hub–74.0%†
CursorBenchCursor57.8%–
ALE-BenchEpoch AI Benchmarking Hub2147.4†933.5†
FrontierSWEEpoch AI Benchmarking Hub62.3%–
Terminal-Bench 4.0 (AA)Artificial Analysis59.6%–
Startrise FrontendStartrise71.1%†–
GameBench 2 OverallDuelLab GameBench 287.6†34.6
GameBench 2 by reasoning settingDuelLab GameBench 294.8†30.5†
Design Arena WebsiteDesign Arena1325†1033
FrontierCode 1.1 (AA)Artificial Analysis52.2%–
FrontierCode 2.0 (AA)Artificial Analysis46.4%–
LiveCodeBench (AA)Artificial Analysis–80.8%
Agents & tools
Terminal-BenchTerminal-Bench65.8%–
GDPvalOpenAI–30.8%†
Remote Labor IndexScale AI / CAIS21.3%†–
APEX-AgentsMercor73.5%–
Arena AgentArena (LMArena)20–
LiveBench Long AgenticLiveBench72.8%†–
LiveBench BrowserLiveBench88.4%†–
LiveBench Agentic CodingLiveBench71.7%–
Terminal-Bench HardArtificial Analysis–37.1%
τ²-Bench Telecom (AA)Artificial Analysis–80.7%
Terminal-Bench 2.1 (Vals)Vals AI87.6%†–
MCP AtlasScale AI SEAL85.4%†–
HiL-BenchScale AI SEAL59.0%†–
BFCL OverallBerkeley Function Calling Leaderboard–63.0%
GDPval-AA v2.1, normalised scoreArtificial Analysis68.3%–
GDPval-AA v2.1Artificial Analysis1866–
ITBench SRE (AA)Artificial Analysis38.2%–
Analyst Agent (AA)Artificial Analysis56.3%–
CUA-benchVals AI14.0%–
CyberBenchVals AI55.4%†–
Finance Agent v2Vals AI58.6%†–
Finance Agent v2.1Vals AI67.8%†–
Harvey's Legal Agent Benchmark v1.1Vals AI9.2%†–
Harvey's Legal Agent Benchmark v1Vals AI3.8%†–
Legal Research BenchVals AI50.5%†–
Robo-benchVals AI14.6%–
SREBenchVals AI33.6%†–
Tax Agent BenchVals AI44.5%†–
Terminal-Bench 4.0 (Vals)Vals AI65.2%†–
Terminal-Bench ScienceVals AI47.1%†–
Time Horizon Index: KSPVals AI91.3%†–
Arena SearchArena (LMArena)1214†1197
DeepResearch BenchDeepResearch Bench–45.2%†
METR Time HorizonsMETR–63.6%
Vending-Bench 2Andon Labs9235.3†–
AutomationBenchArtificial Analysis69.5%–
GDP.pdf (AA)Artificial Analysis26.2%–
Harvey LAB-AA v1.1Harvey4.2%–
AA-Briefcase v1.1Artificial Analysis1800–
GDPxGDPx by SemiAnalysis12.0%–
Design Arena AgenticDesign Arena1334†–
Terminal-Bench-Science 0.1 (AA)Artificial Analysis59.0%–
CWE-Bench (AA)Artificial Analysis58.3%–
DeepSec-Bench (AA)Artificial Analysis26.9%–
CyberGym end-to-end (AA)Artificial Analysis0.8%–
BrowseComp-PlusBrowseComp-Plus–50.5%
FACTS SearchGoogle88.4%†–
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub91.2%33.3%†
FrontierMath Tier 4Epoch AI Benchmarking Hub95.0%–
OTIS Mock AIMEEpoch AI Benchmarking Hub100.0%83.9%†
MATH Level 5Epoch AI Benchmarking Hub–97.8%†
ProofBenchVals AI100.0%–
LiveBench MathematicsLiveBench97.1%–
AIME (Vals)Vals AI–85.3%†
MGSMVals AI–91.8%†
IMO 2025MathArena–16.7%†
Omni-MATH (HELM)HELM Capabilities–71.4%
MATH 500Vals AI–94.6%†
Arena MathsArena (LMArena)1518†1448
AIME 2025 (AA)Artificial Analysis–88.3%
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub72.2%49.4%†
LiveBench 2.0 Data AnalysisLiveBench80.3%†–
LiveBench ResearchLiveBench88.9%†–
LiveBench 1.0 Data AnalysisLiveBench80.3%–
AA-Omniscience v1.1Artificial Analysis48.1–
MMLU-ProVals AI–85.6%†
LegalBenchVals AI–83.8%†
CorpFinVals AI–59.7%†
TaxEvalVals AI–74.6%†
MedQAVals AI–96.1%†
PRBench FinanceScale AI SEAL–47.7%
PRBench LegalScale AI SEAL47.6%†48.6%
MultiNRCScale AI SEAL–45.5%†
MMLU-Pro (HELM)HELM Capabilities–85.9%
BioMysteryBenchVals AI79.3%†–
ClaimBenchVals AI100.0%†–
Excel Modeling BenchmarkVals AI75.9%†–
Excel Modeling Benchmark v1.1Vals AI75.8%†–
MedCodeVals AI49.8%†47.3%†
MedScribeVals AI91.4%†76.7%†
Public Benefits Bench v1.1Vals AI70.6%†–
EBR-benchEpoch AI Benchmarking Hub71.4%–
GDP.pdfEpoch AI Benchmarking Hub30.6%–
AA-Omniscience v1.1: accuracyArtificial Analysis65.5%–
AA-Omniscience v1.1: non-hallucinationArtificial Analysis49.7%–
HealthBench Professional (AA)OpenAI59.9%–
Instruction following
LiveBench LanguageLiveBench86.3%–
LiveBench Instruction FollowingLiveBench65.7%–
IFBenchArtificial Analysis–71.4%
MultiChallengeScale AI SEAL–56.6%†
TutorBenchScale AI SEAL–52.1%†
IFEval (HELM)HELM Capabilities–86.9%
WildBench (HELM)HELM Capabilities–86.1%
Arena Instruction FollowingArena (LMArena)1519†1403
Human preference
Arena TextArena (LMArena)1506†1432
EQ-Bench 4EQ-Bench1340†–
Arena Creative WritingArena (LMArena)1517†1383
Arena Multi-turnArena (LMArena)1500†1420
Arena Longer QueriesArena (LMArena)1520†1411
Lech Mazur Creative WritingLech Mazur–83.9%†
Multimodal
Arena VisionArena (LMArena)1324†1214
LiveBench DesignLiveBench83.3%†–
MMMU-ProArtificial Analysis87.7%70.1%
VISTAScale AI SEAL–50.1%†
MMMU (validation)MMMU–82.9%
MMMU-Pro (official)MMMU–76.4%
MMMU-Pro (Vals)Vals AI–80.4%†
MortgageTaxVals AI–65.7%†
SAGEVals AI91.3%†–
VTBScale AI SEAL–13.7%
GeoBenchGeoBench–60.0%†
VPCTEpoch AI Benchmarking Hub–52.0%†
Blueprint-Bench 2Epoch AI Benchmarking Hub51.2%†–
Code2Video-AAArtificial Analysis1536–
AA-3DArtificial Analysis1202–
Long context
Fiction.LiveBench 120kFiction.live–100.0%†
AA-LCR v1.1Artificial Analysis84.7%74.7%
MLCRArtificial Analysis27.8%–
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub168.4†147.0
LiveBench 2.0LiveBench83.4%†–
LiveBench 1.0LiveBench83.2%–
AA Intelligence Index v5.0Artificial Analysis59.1–
AA Intelligence Index v4.3.2Artificial Analysis57.620.2
AA Progress Index v1Artificial Analysis350258.3
Vals IndexVals AI70.1†–
HELM Capabilities meanHELM Capabilities–81.1%
Vals Finance IndexVals AI65.3%†–
Vals RSI IndexVals AI37.3%–
Vals Science IndexVals AI58.6%†–
Vals Router IndexVals AI64.2%†–
AA Cyber IndexArtificial Analysis28.7–
Safety & honesty
FORTRESSScale AI SEAL5.8%16.0%
MASKScale AI SEAL–84.5%†
PropensityBenchScale AI SEAL–10.5%

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.
  • o3: 1 new result (Arena Search).
  • Claude Opus 5.5 (max): 1 score revision.
  • Claude Opus 5.5 (max): 2 score revisions.
  • o3: 1 score revision.
  • Claude Opus 5.5 (max): 2 score revisions.
  • Claude Opus 5.5 (max): 1 score revision.
  • 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).
  • o3: 1 new result (AA Progress Index v1).

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

Claude Opus 5.5 vs o3: questions

Is Claude Opus 5.5 better than o3?
Claude Opus 5.5 (max) leads on quality: 68.9 vs 61.0. 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 5.5 vs o3: which is cheaper, and will that change?
o3 is cheaper today: $3.50 against $8.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Is Claude Opus 5.5 or o3 better for coding?
Claude Opus 5.5 scores higher in coding (80 vs 62 on the category index, where 50 is average).
Which is faster, Claude Opus 5.5 or o3?
Claude Opus 5.5 streams faster (115 vs 112 output tokens per second, Artificial Analysis 7-day median).
Is Claude Opus 5.5 or o3 better for agents and tool use?
o3 scores higher in agentic tasks (70 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 62). Claude Opus 5.5 accepts more context: 1,000,000 against 200,000 tokens for o3.
Which has lower latency?
o3 answers first: 5.3 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 5.5 vs o3?
Across the 6 benchmarks both have, Claude Opus 5.5 leads 5, o3 leads 1. 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.