BenchLeader
Menu
Best LLMsChoose a modelCoding plansLeaderboardsModelsBenchmarksProvidersReleases12

Claude Fable 5.1 vs Claude Opus 5.5

Full profiles: Claude Fable 5.1 (Anthropic) and Claude Opus 5.5 (Anthropic): every benchmark, price and rank.

Updated · Data from 12 sources

As of 9 Nov 2026, Claude Fable 5.1 and Claude Opus 5.5 are neck and neck on quality (66.9 vs 68.9 on the BenchLeader Index, inside the ±6.1 margin), and Claude Opus 5.5 is 2.5× cheaper at $8.00 vs $20.00 per 1M tokens blended. Claude Opus 5.5 leads in every category we measure both in. Claude Opus 5.5 streams faster.

Key facts (as of 9 Nov 2026)

  • Claude Fable 5.1 scores 66.9 on the BenchLeader Index and Claude Opus 5.5 scores 68.9 (BenchLeader, 9 Nov 2026).
  • Claude Fable 5.1 costs $20.00 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 faster than Claude Fable 5.1 (Artificial Analysis, 7-day median, 9 Nov 2026).
  • Of the 57 benchmarks both models have, Claude Opus 5.5 leads 44 (BenchLeader, 9 Nov 2026).
  • On Arena WebDev, Claude Fable 5.1 is rated 1744 and Claude Opus 5.5 1818 (LMArena, as published by 9 Nov 2026).
Claude Fable 5.1 benchmarks max 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 71 category score; Arena WebDev 1818 vs 1744High
Agents & tool useClaude Opus 5.563 vs 60 category score; Terminal-Bench 65.8% vs 57.3%Medium
MathsClaude Opus 5.574 vs 73 category score; FrontierMath Tiers 1–3 91.2% vs 90.2%Medium
ReasoningClaude Opus 5.572 vs 70 category score; HLE-Diamond (AA) 67.9% vs 60.1%Medium
KnowledgeClaude Opus 5.574 vs 73 category score; SimpleQA Verified 72.2% vs 70.8%Medium
Long documentsEither68 vs 67 category score; AA-LCR v1.1 85.3% vs 84.7%Either
Images and other mediaClaude Opus 5.570 vs 67 category score; Code2Video-AA 1536 vs 1325Medium
Chat quality (human preference)–Only Claude Fable 5.1 has an Arena rating (70 category score)Not comparable
Lowest costClaude Opus 5.5$8.00 vs $20.00 per 1M blended; agentic coding session $0.320 vs $0.800–
Fastest first answerClaude Fable 5.1171.7 s (Claude Fable 5.1 (max)) 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 Fable 5.1 (max) and Claude Opus 5.5 (max) are neck and neck on quality (66.9 vs 68.9, within the ±6.1 margin).
  • Claude Fable 5.1 (max) is stronger in human preference, long context.
  • Claude Opus 5.5 (max) is stronger in agents & tools, coding, knowledge, maths, multimodal, reasoning.
  • Claude Opus 5.5 (max) is 2.5× cheaper ($8.00 vs $20.00 per 1M blended).
  • Claude Opus 5.5 (max) streams 1.3× faster (115 vs 87 tokens per second).

At a glance

SpecClaude Fable 5.1Claude Opus 5.5
DeveloperAnthropicAnthropic
Released1 Sep 202622 Sep 2026
Context window (tokens)1,000,0001,000,000
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 Fable 5.1 (max)Claude Opus 5.5 (max)
Open weightsNoNo
Price in / out / cached input per 1M$10.00 / $50.00 / $0.250$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 Fable 5.1 (max)Claude Opus 5.5 (max)Leader
Reasoning69.672.3Claude Opus 5.5
Coding70.980.4Claude Opus 5.5
Agents & tools60.362.7Claude Opus 5.5
Maths72.574.0Claude Opus 5.5
Knowledge72.673.7Claude Opus 5.5
Human preference69.9–not comparable
Multimodal67.470.3Claude Opus 5.5
Long context67.567.1level

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 Fable 5.1, Reasoning: 69.6Claude Fable 5.1, Coding: 70.9Claude Fable 5.1, Agents & tools: 60.3Claude Fable 5.1, Maths: 72.5Claude Fable 5.1, Knowledge: 72.6Claude Fable 5.1, Long context: 67.5Claude Fable 5.1, Multimodal: 67.4Claude 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 57 benchmarks both have, Claude Fable 5.1 leads 8, Claude Opus 5.5 leads 44 and 5 are tied. Every overall index that rates both puts Claude Opus 5.5 ahead.

Overall indexClaude Fable 5.1 (max)Claude Opus 5.5 (max)Leader
BenchLeader Index66.968.9neck and neck
AA Intelligence Index v5.049.259.1Claude Opus 5.5
Arena Text15031506†Claude 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 Fable 5.1 (max)Claude Opus 5.5 (max)
Blended price per 1M tokens$20.00$8.00
Input / output per 1M$10.00 / $50.00$4.00 / $20.00
Cached input per 1M$0.250$0.200
Price per task: chat reply$0.019$0.0076
Price per task: summarize a 30-page report$0.150$0.060
Price per task: code edit$0.135$0.054
Price per task: agentic coding session$0.800$0.320
Price per task: structured extraction$0.030$0.012
Agentic coding session, input mostly cached$0.361$0.149
Cost per benchmark task (AA Index)$12.99$10.04
Output tokens per task (AA Index)118k173k
Of which reasoning71k120k
Time per task (AA Index)23 min25 min
Output speed87 tok/s115 tok/s
Time to first answer171.7 s380.6 s
Time to a complete answer403.1 s771.1 s

Per token is not per task: an average task of Artificial Analysis' Intelligence Index cost $12.99 on Claude Fable 5.1 (max) and $10.04 on Claude Opus 5.5 (max), and Claude Opus 5.5 (max) wrote 1.5× as many output tokens for the same work, which a per-token price hides.

Each model is compared at its best-ranked reasoning-effort setting. Claude Fable 5.1 (max) scores 66.9 and takes 172 s to its first answer token; Claude Fable 5.1 scores 66.0 in 3 s, Claude Fable 5.1 (xhigh) scores 64.6 in 59 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

152 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 Fable 5.1 (max)Claude Opus 5.5 (max)
BenchLeader IndexBenchLeader66.968.9
Agents & tools scoreBenchLeader60.362.7
Coding scoreBenchLeader70.980.4
Human preference scoreBenchLeader69.9–
Knowledge scoreBenchLeader72.673.7
Long context scoreBenchLeader67.567.1
Maths scoreBenchLeader72.574.0
Multimodal scoreBenchLeader67.470.3
Reasoning scoreBenchLeader69.672.3
Blended price $/MBenchLeader$20.00$8.00
Output speedBenchLeader87 tok/s115 tok/s
Time to first answerBenchLeader171.7 s380.6 s
Context windowBenchLeader1,000,000 tokens1,000,000 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub–90.6%
Humanity's Last ExamScale AI / CAIS46.5%†–
Arena Hard PromptsArena (LMArena)15211530†
LiveBench 2.0 ReasoningLiveBench91.7%†92.2%†
LiveBench 1.0 ReasoningLiveBench91.7%92.2%
GPQA Diamond (AA)Artificial Analysis93.7%–
Humanity's Last Exam (AA)Artificial Analysis59.1%61.4%
HLE-Diamond (AA)Artificial Analysis60.1%67.9%
GPQA Diamond (Vals)Vals AI93.4%†–
ARC-AGI-1ARC Prize97.5%97.5%
ARC-AGI-2ARC Prize90.0%91.7%
CritPtArtificial Analysis29.7%31.7%
CritPt v2 hard subset (AA)Artificial Analysis52.5%68.0%
MysteryMechanismVals AI47.8%†49.5%†
Chess PuzzlesEpoch AI Benchmarking Hub48.0%67.0%
Mystery Game PuzzlesEpoch AI Benchmarking Hub58.0%71.0%
LMCAEpoch AI Benchmarking Hub65.5%†68.2%
DTBenchEpoch AI Benchmarking Hub97.6%†98.9%
Coding
SciCodeSciCode63.1%66.9%
WeirdMLWeirdML92.9%–
FrontierCodeCognition50.9%†54.6%†
GSO-BenchGSO-Bench88.2%†–
Arena CodingArena (LMArena)15341546†
Arena WebDevArena (LMArena)17441818
LiveBench 2.0 CodingLiveBench89.7%†87.1%†
Show all 152 benchmarks
MetricPublisherClaude Fable 5.1 (max)Claude Opus 5.5 (max)
Coding
LiveBench 1.0 CodingLiveBench86.4%89.3%
LiveCodeBenchVals AI90.5%†–
IOIVals AI90.8%†95.1%†
Code MigrationVals AI54.6%†66.7%†
Code Migration v1.1Vals AI–81.0%†
ProgramBenchVals AI7.0%†18.5%†
SWE-bench MultimodalVals AI61.3%†70.2%†
Vibe Code Bench 1-100Vals AI28.0%†30.4%†
Vibe Code Bench v1.1Vals AI90.3%†90.3%†
SWE Atlas: Codebase QnAScale AI SEAL60.0%†–
SWE Atlas: RefactoringScale AI SEAL56.7%†–
SWE Atlas: Test WritingScale AI SEAL67.0%†–
MirrorCodeEpoch AI Benchmarking Hub73.3%†78.9%†
CursorBenchCursor51.8%57.8%
ALE-BenchEpoch AI Benchmarking Hub2143.2†2147.4†
FrontierSWEEpoch AI Benchmarking Hub56.3%62.3%
Terminal-Bench 4.0 (AA)Artificial Analysis52.0%59.6%
Terminal-Bench 2.1 (AA)Artificial Analysis91.4%–
Startrise FrontendStartrise77.1%†71.1%†
GameBench 2 OverallDuelLab GameBench 287.2†87.6†
GameBench 2 by reasoning settingDuelLab GameBench 294.1†94.8†
Design Arena WebsiteDesign Arena1306†1325†
FrontierCode 1.1 (AA)Artificial Analysis49.0%52.2%
FrontierCode 2.0 (AA)Artificial Analysis31.6%46.4%
Agents & tools
Terminal-BenchTerminal-Bench57.3%65.8%
Remote Labor IndexScale AI / CAIS17.9%†21.3%†
APEX-AgentsMercor68.6%†73.5%
Arena AgentArena (LMArena)14.320
LiveBench Long AgenticLiveBench74.2%†72.8%†
LiveBench BrowserLiveBench89.8%†88.4%†
LiveBench Agentic CodingLiveBench66.1%71.7%
Terminal-Bench 2.1 (Vals)Vals AI85.0%†87.6%†
MCP AtlasScale AI SEAL87.2%†85.4%†
HiL-BenchScale AI SEAL61.5%†59.0%†
GDPval-AA v2.1, normalised scoreArtificial Analysis62.7%68.3%
GDPval-AA v2.1Artificial Analysis–1866
τ³-Banking (AA)Artificial Analysis47.2%–
ITBench SRE (AA)Artificial Analysis49.5%38.2%
Analyst Agent (AA)Artificial Analysis57.5%56.3%
CUA-benchVals AI13.2%14.0%
CyberBenchVals AI70.4%†55.4%†
Finance Agent v2Vals AI58.9%†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 AI6.7%†3.8%†
Legal Research BenchVals AI55.3%†50.5%†
Robo-benchVals AI5.8%14.6%
SkillsBenchVals AI61.5%†–
SREBenchVals AI22.9%†33.6%†
Tax Agent BenchVals AI50.8%†44.5%†
Terminal-Bench 4.0 (Vals)Vals AI58.1%†65.2%†
Terminal-Bench ScienceVals AI40.0%†47.1%†
Time Horizon Index: KSPVals AI63.3%†91.3%†
Arena SearchArena (LMArena)1229†1214†
Vending-Bench 2Andon Labs5421.6†9235.3†
AutomationBenchArtificial Analysis59.4%69.5%
GDP.pdf (AA)Artificial Analysis26.2%26.2%
Harvey LAB-AA v1.1Harvey6.4%4.2%
AA-Briefcase v1.1Artificial Analysis16691800
GDPxGDPx by SemiAnalysis8.5%12.0%
Design Arena AgenticDesign Arena1332†1334†
Terminal-Bench-Science 0.1 (AA)Artificial Analysis43.3%59.0%
CWE-Bench (AA)Artificial Analysis50.8%58.3%
DeepSec-Bench (AA)Artificial Analysis23.5%26.9%
CyberGym end-to-end (AA)Artificial Analysis0.8%0.8%
FACTS SearchGoogle–88.4%†
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub90.2%91.2%
FrontierMath Tier 4Epoch AI Benchmarking Hub87.8%95.0%
OTIS Mock AIMEEpoch AI Benchmarking Hub100.0%100.0%
ProofBenchVals AI100.0%100.0%
LiveBench MathematicsLiveBench97.0%97.1%
Arena MathsArena (LMArena)15251518†
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub70.8%72.2%
LiveBench 2.0 Data AnalysisLiveBench80.3%†80.3%†
LiveBench ResearchLiveBench88.5%†88.9%†
LiveBench 1.0 Data AnalysisLiveBench80.3%80.3%
AA-Omniscience v1.1Artificial Analysis46.348.1
MMLU-ProVals AI92.4%†–
LegalBenchVals AI88.5%†–
TaxEvalVals AI76.0%†–
PRBench FinanceScale AI SEAL50.8%†–
PRBench LegalScale AI SEAL51.6%†47.6%†
BioMysteryBenchVals AI–79.3%†
ClaimBenchVals AI–100.0%†
Excel Modeling BenchmarkVals AI76.7%†75.9%†
Excel Modeling Benchmark v1.1Vals AI76.7%†75.8%†
MedCodeVals AI53.5%†49.8%†
MedScribeVals AI91.3%†91.4%†
Public Benefits Bench v1.1Vals AI74.9%†70.6%†
EBR-benchEpoch AI Benchmarking Hub57.1%71.4%
GDP.pdfEpoch AI Benchmarking Hub27.6%30.6%
AA-Omniscience v1.1: accuracyArtificial Analysis68.4%65.5%
AA-Omniscience v1.1: non-hallucinationArtificial Analysis30.0%49.7%
HealthBench Professional (AA)OpenAI57.8%59.9%
Instruction following
LiveBench LanguageLiveBench89.5%86.3%
LiveBench Instruction FollowingLiveBench73.0%65.7%
Arena Instruction FollowingArena (LMArena)15011519†
Human preference
Arena TextArena (LMArena)15031506†
EQ-Bench 4EQ-Bench–1340†
Arena Creative WritingArena (LMArena)14901517†
Arena Multi-turnArena (LMArena)14871500†
Arena Longer QueriesArena (LMArena)15101520†
Multimodal
Arena VisionArena (LMArena)13221324†
LiveBench DesignLiveBench81.6%†83.3%†
MMMU-ProArtificial Analysis–87.7%
MMMU-Pro (Vals)Vals AI90.6%†–
MortgageTaxVals AI70.8%†–
SAGEVals AI–91.3%†
Blueprint-Bench 2Epoch AI Benchmarking Hub41.9%†51.2%†
Code2Video-AAArtificial Analysis13251536
AA-3DArtificial Analysis11391202
Long context
AA-LCR v1.1Artificial Analysis85.3%84.7%
Arena DocumentArena (LMArena)1498–
MLCRArtificial Analysis15.6%27.8%
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub166.9†168.4†
LiveBench 2.0LiveBench84.0%†83.4%†
LiveBench 1.0LiveBench83.4%83.2%
AA Intelligence Index v5.0Artificial Analysis49.259.1
AA Intelligence Index v4.3.2Artificial Analysis53.457.6
AA Progress Index v1Artificial Analysis340.8350
Vals IndexVals AI–70.1†
Vals Finance IndexVals AI–65.3%†
Vals RSI IndexVals AI36.1%37.3%
Vals Science IndexVals AI–58.6%†
Vals Router IndexVals AI–64.2%†
AA Cyber IndexArtificial Analysis25.028.7
Safety & honesty
FORTRESSScale AI SEAL13.7%†5.8%

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 Fable 5.1 (max): 1 score revision.
  • Claude Opus 5.5 (max): 2 score revisions.
  • Claude Fable 5.1 (max): 1 score revision.
  • Claude Opus 5.5 (max): 1 score revision.
  • Claude Fable 5.1 (max): 1 score revision.
  • Claude Opus 5.5 (max): 1 score revision.
  • Claude Fable 5.1 (max): 1 score revision.
  • Claude Opus 5.5 (max): 2 score revisions.
  • Claude Opus 5.5 (max): 2 score revisions.
  • Claude Fable 5.1 (max): 1 new result (MirrorCode).

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

Claude Fable 5.1 vs Claude Opus 5.5: questions

Is Claude Fable 5.1 better than Claude Opus 5.5?
Claude Fable 5.1 (max) and Claude Opus 5.5 (max) are neck and neck on quality (66.9 vs 68.9, within the ±6.1 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 9 Nov 2026, so check the category scores for your use.
Claude Fable 5.1 vs Claude Opus 5.5: which is cheaper, and will that change?
Claude Opus 5.5 is cheaper today: $8.00 against $20.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Is Claude Fable 5.1 or Claude Opus 5.5 better for coding?
Claude Opus 5.5 scores higher in coding (80 vs 71 on the category index, where 50 is average). On Arena WebDev, the top shared coding benchmark, it is 1744 for Claude Fable 5.1 against 1818 for Claude Opus 5.5.
Which is faster, Claude Fable 5.1 or Claude Opus 5.5?
Claude Opus 5.5 streams faster (115 vs 87 output tokens per second, Artificial Analysis 7-day median).
Is Claude Fable 5.1 or Claude Opus 5.5 better for agents and tool use?
Claude Opus 5.5 scores higher in agentic tasks (63 vs 60 on the category index, where 50 is average). On Terminal-Bench, the top shared agents & tools benchmark, it is 57.3% for Claude Fable 5.1 against 65.8% for Claude Opus 5.5.
More questions (4)
Which is better for long documents?
They are level on long-context benchmarks (68 vs 67). Both accept 1,000,000 tokens of context.
Which has lower latency?
Claude Fable 5.1 answers first: 171.7 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 Fable 5.1 vs Claude Opus 5.5?
Across the 57 benchmarks both have, Claude Fable 5.1 leads 8, Claude Opus 5.5 leads 44 and 5 are tied. 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.