BenchLeader

Claude Fable 5.1 vs GPT-6.2 Astra

Full profiles: Claude Fable 5.1 (Anthropic) and GPT-6.2 Astra (OpenAI): every benchmark, price and rank.

Updated · Data from 12 sources

As of 19 Nov 2026, Claude Fable 5.1 and GPT-6.2 Astra are neck and neck on quality (66.4 vs 68.9 on the BenchLeader Index, inside the ±3.5 margin), and GPT-6.2 Astra is 1.3× cheaper at $16.00 vs $20.00 per 1M tokens blended. GPT-6.2 Astra leads in every category we measure both in. Claude Fable 5.1 streams ~1.5× faster.

Key facts (as of 19 Nov 2026)

  • Claude Fable 5.1 scores 66.4 on the BenchLeader Index and GPT-6.2 Astra scores 68.9 (BenchLeader, 19 Nov 2026).
  • Claude Fable 5.1 costs $20.00 per 1M tokens blended (list price, 19 Nov 2026).
  • GPT-6.2 Astra costs $16.00 per 1M tokens blended (list price, 19 Nov 2026).
  • Claude Fable 5.1 streams ~1.5× faster than GPT-6.2 Astra (Artificial Analysis, 7-day median, 19 Nov 2026).
  • Of the 53 benchmarks both models have, GPT-6.2 Astra leads 41 (BenchLeader, 19 Nov 2026).
  • On Arena WebDev, Claude Fable 5.1 is rated 1741 and GPT-6.2 Astra 1781 (LMArena, as published by 19 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
CodingGPT-6.2 Astra76 vs 69 category score; Arena WebDev 1781 vs 1741Medium
Agents & tool useGPT-6.2 Astra66 vs 62 category score; Terminal-Bench 62.1% vs 57.3%Medium
MathsEither72 vs 73 category score; FrontierMath Tiers 1–3 90.2% vs 92.6%Either
ReasoningGPT-6.2 Astra73 vs 68 category score; HLE-Diamond (AA) 72.2% vs 60.1%Medium
KnowledgeGPT-6.2 Astra74 vs 68 category score; SimpleQA Verified 78.5% vs 70.8%Medium
Images and other mediaGPT-6.2 Astra72 vs 68 category score; LiveBench Design 82.8% vs 81.6%Medium
Chat quality (human preference)–Only Claude Fable 5.1 has an Arena rating (70 category score)Not comparable
Lowest costGPT-6.2 Astra$16.00 vs $20.00 per 1M blended; agentic coding session $0.640 vs $0.800–
Fastest first answerClaude Fable 5.1140.2 s (Claude Fable 5.1 (max)) vs 202.7 s (GPT-6.2 Astra (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 GPT-6.2 Astra (max) are neck and neck on quality (66.4 vs 68.9, within the ±3.5 margin).
  • GPT-6.2 Astra (max) is stronger in agents & tools, coding, composite, knowledge, maths, multimodal, reasoning.
  • GPT-6.2 Astra (max) is 1.3× cheaper ($16.00 vs $20.00 per 1M blended).
  • Claude Fable 5.1 (max) streams 1.9× faster (90 vs 49 tokens per second).

At a glance

SpecClaude Fable 5.1GPT-6.2 Astra
DeveloperAnthropicOpenAI
Released1 Sep 202617 Nov 2026
Context window (tokens)1,000,0001,050,000
Compared atClaude Fable 5.1 (max)GPT-6.2 Astra (max)
Open weightsNoNo
Price in / out / cached input per 1M$10.00 / $50.00 / $0.250$8.00 / $40.00 / $0.400

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)GPT-6.2 Astra (max)Leader
Reasoning68.073.1GPT-6.2 Astra
Coding69.076.1GPT-6.2 Astra
Agents & tools62.066.4GPT-6.2 Astra
Maths71.772.5level
Knowledge68.074.2GPT-6.2 Astra
Human preference69.7–not comparable
Multimodal67.571.7GPT-6.2 Astra
Long context67.4–not comparable
Composite68.569.5GPT-6.2 Astra

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 & toolsMathsKnowledgeMultimodalClaude Fable 5.1, Reasoning: 68.0Claude Fable 5.1, Coding: 69.0Claude Fable 5.1, Agents & tools: 62.0Claude Fable 5.1, Maths: 71.7Claude Fable 5.1, Knowledge: 68.0Claude Fable 5.1, Multimodal: 67.5GPT-6.2 Astra, Reasoning: 73.1GPT-6.2 Astra, Coding: 76.1GPT-6.2 Astra, Agents & tools: 66.4GPT-6.2 Astra, Maths: 72.5GPT-6.2 Astra, Knowledge: 74.2GPT-6.2 Astra, Multimodal: 71.7

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

Model, click to add or removeIndex

Where sources disagree

Across the 53 benchmarks both have, Claude Fable 5.1 leads 11, GPT-6.2 Astra leads 41 and 1 is a tie. Every overall index that rates both puts GPT-6.2 Astra ahead.

Overall indexClaude Fable 5.1 (max)GPT-6.2 Astra (max)Leader
BenchLeader Index66.468.9neck and neck
AA Intelligence Index v5.0.149.262.1GPT-6.2 Astra

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)GPT-6.2 Astra (max)
Blended price per 1M tokens$20.00$16.00
Input / output per 1M$10.00 / $50.00$8.00 / $40.00
Cached input per 1M$0.250$0.400
Price per task: chat reply$0.019$0.015
Price per task: summarize a 30-page report$0.150$0.120
Price per task: code edit$0.135$0.108
Price per task: agentic coding session$0.800$0.640
Price per task: structured extraction$0.030$0.024
Agentic coding session, input mostly cached$0.361$0.298
Cost per benchmark task (AA Index)$12.99$4.00
Output tokens per task (AA Index)118k41k
Of which reasoning71k26k
Time per task (AA Index)22 min14 min
Output speed90 tok/s49 tok/s
Time to first answer140.2 s202.7 s
Time to a complete answer, last measured 13 Nov 2026386.7 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 $4.00 on GPT-6.2 Astra (max), and Claude Fable 5.1 (max) wrote 2.9× 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 66.4 and takes 140 s to its first answer token; Claude Fable 5.1 scores 66.1 in 3 s, Claude Fable 5.1 (xhigh) scores 63.9 in 40 s. GPT-6.2 Astra (max) scores 68.9 and takes 203 s to its first answer token; GPT-6.2 Astra (xhigh) scores 67.1 in 67 s, GPT-6.2 Astra (medium) scores 65.6 in 4 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

177 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)GPT-6.2 Astra (max)
BenchLeader IndexBenchLeader66.468.9
Agents & tools scoreBenchLeader62.066.4
Coding scoreBenchLeader69.076.1
Composite scoreBenchLeader68.569.5
Human preference scoreBenchLeader69.7–
Knowledge scoreBenchLeader68.074.2
Long context scoreBenchLeader67.4–
Maths scoreBenchLeader71.772.5
Multimodal scoreBenchLeader67.571.7
Reasoning scoreBenchLeader68.073.1
Blended price $/MBenchLeader$20.00$16.00
Output speedBenchLeader90 tok/s49 tok/s
Time to first answerBenchLeader140.2 s202.7 s
Context windowBenchLeader1,000,000 tokens1,050,000 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub–96.8%
Humanity's Last ExamScale AI / CAIS46.5%†–
SimpleBenchSimpleBench86.6%†–
Arena Hard PromptsArena (LMArena)1521–
LiveBench 2.0 ReasoningLiveBench91.7%91.6%
LiveBench 1.0 ReasoningLiveBench91.7%–
GPQA Diamond (AA)Artificial Analysis93.7%–
Humanity's Last Exam (AA)Artificial Analysis59.1%–
HLE-Diamond (AA)Artificial Analysis60.1%72.2%
GPQA Diamond (Vals)Vals AI93.4%–
ARC-AGI-1ARC Prize97.5%98.5%
ARC-AGI-2ARC Prize90.0%95.8%
ARC-AGI-3ARC Prize–99.8%
CritPtArtificial Analysis29.7%–
CritPt v2 hard subset (AA)Artificial Analysis52.5%71.5%
MysteryMechanismVals AI47.8%53.1%
HLE-Diamond (Scale)Scale AI SEAL51.3%†66.9%†
Arena ExpertArena (LMArena)1534–
Chess PuzzlesEpoch AI Benchmarking Hub48.0%78.0%
Mystery Game PuzzlesEpoch AI Benchmarking Hub58.0%95.0%
LMCAEpoch AI Benchmarking Hub65.5%†–
DTBenchEpoch AI Benchmarking Hub97.6%†–
ForecastBenchForecastBench65.8%†–
Coding
SciCodeSciCode63.1%–
WeirdMLWeirdML92.9%–
Show all 177 benchmarks
MetricPublisherClaude Fable 5.1 (max)GPT-6.2 Astra (max)
Coding
FrontierCodeCognition50.9%†–
GSO-BenchGSO-Bench88.2%†–
Arena CodingArena (LMArena)1532–
Arena WebDevArena (LMArena)17411781
LiveBench 2.0 CodingLiveBench89.7%91.9%
LiveBench 1.0 CodingLiveBench86.4%–
LiveCodeBenchVals AI90.5%–
IOIVals AI90.8%–
Code MigrationVals AI54.6%–
ProgramBenchVals AI7.0%–
SWE-bench MultimodalVals AI61.3%–
Vibe Code Bench 1-100Vals AI28.0%–
Vibe Code Bench v1.1Vals AI90.3%89.9%
Vibe Code Bench 1-100 v1.1Vals AI–55.2%
SWE Atlas v1.0: Codebase QnAScale AI SEAL60.0%†–
SWE Atlas v1.0: RefactoringScale AI SEAL56.7%†–
SWE Atlas v1.0: Test WritingScale AI SEAL67.0%†–
SWE Atlas v1.1Scale AI SEAL76.5%†60.5%†
SWE Atlas v1.1: Codebase QnAScale AI SEAL79.0%†67.7%†
SWE Atlas v1.1: Test WritingScale AI SEAL78.9%†62.2%†
SWE Atlas v1.1: RefactoringScale AI SEAL71.4%†51.4%†
SWE-Bench Pro V2Scale AI SEAL99.1%†–
SWE-Bench Pro V2 HARDScale AI SEAL92.2%†–
MirrorCodeEpoch AI Benchmarking Hub93.3%67.8%
CursorBenchCursor51.8%–
ALE-BenchEpoch AI Benchmarking Hub2143.2†–
FrontierSWEEpoch AI Benchmarking Hub56.3%–
WeirdML v3WeirdML26.0%†–
Terminal-Bench 4.0 (AA)Artificial Analysis52.0%64.1%
Terminal-Bench 2.1 (AA)Artificial Analysis91.4%–
Startrise FrontendStartrise77.1%†–
GameBench 2 OverallDuelLab GameBench 287.1†–
GameBench 2 by reasoning settingDuelLab GameBench 294†–
Design Arena WebsiteDesign Arena1298†1339†
FrontierCode 1.1 (AA)Artificial Analysis49.0%–
FrontierCode 2.0 (AA)Artificial Analysis31.6%45.4%
Agents & tools
Terminal-BenchTerminal-Bench57.3%62.1%
Remote Labor IndexScale AI / CAIS17.9%†–
APEX-AgentsMercor68.6%†–
Arena AgentArena (LMArena)13.715.2
LiveBench Long AgenticLiveBench74.2%70.8%
LiveBench BrowserLiveBench89.8%93.0%
LiveBench Agentic CodingLiveBench66.1%–
Terminal-Bench 2.1 (Vals)Vals AI85.0%†–
MCP AtlasScale AI SEAL87.2%†–
HiL-BenchScale AI SEAL61.5%†–
GDPval-AA v2.1, normalised scoreArtificial Analysis62.7%–
GDPval-AA v2.1Artificial Analysis1765–
τ³-Banking (AA)Artificial Analysis47.2%–
ITBench SRE (AA)Artificial Analysis49.5%–
Analyst Agent (AA)Artificial Analysis57.5%62.5%
CUA-benchVals AI13.2%–
CyberBenchVals AI70.4%–
Finance Agent v2Vals AI58.9%–
Finance Agent v2.1Vals AI–60.8%
Harvey's Legal Agent Benchmark v1.1Vals AI–16.3%
Harvey's Legal Agent Benchmark v1Vals AI6.7%–
Legal Research BenchVals AI55.3%42.8%
Robo-benchVals AI5.8%32.7%
SkillsBenchVals AI61.5%–
SREBenchVals AI22.9%–
Tax Agent BenchVals AI50.8%21.8%
Terminal-Bench 4.0 (Vals)Vals AI58.1%63.1%
Terminal-Bench ScienceVals AI40.0%71.4%
Time Horizon Index: KSPVals AI63.3%–
Arena SearchArena (LMArena)1227†–
Arena Agent Task CompletionArena (LMArena)14.212.4
PostTrainBenchEpoch AI Benchmarking Hub44.6%–
Vending-Bench 2Andon Labs5421.6†–
SpireClimbEpoch AI Benchmarking Hub2.0%41.3%
AutomationBenchArtificial Analysis59.4%77.3%
GDP.pdf (AA)Artificial Analysis26.2%29.8%
Harvey LAB-AA v1.1Harvey6.4%15.0%
EnterpriseOps-GymArtificial Analysis–29.9%
AA-Briefcase v1.1Artificial Analysis16711643
GDPxGDPx by SemiAnalysis8.5%–
Design Arena AgenticDesign Arena1332†1304
Terminal-Bench-Science 0.1 (AA)Artificial Analysis43.3%78.1%
CWE-Bench (AA)Artificial Analysis50.8%65.0%
DeepSec-Bench (AA)Artificial Analysis23.5%46.8%
CyberGym end-to-end (AA)Artificial Analysis0.8%0.0%
MKA (AA)Artificial Analysis–52.7%
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub90.2%92.6%
FrontierMath Tier 4Epoch AI Benchmarking Hub87.8%100.0%
OTIS Mock AIMEEpoch AI Benchmarking Hub100.0%100.0%
ProofBenchVals AI100.0%–
LiveBench MathematicsLiveBench97.0%–
Autoform-HardVals AI–87.5%
Arena MathsArena (LMArena)1528–
FrontierMath ErdősEpoch AI Benchmarking Hub0.0%10.3%
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub70.8%78.5%
LiveBench 2.0 Data AnalysisLiveBench80.3%84.1%
LiveBench ResearchLiveBench88.5%91.5%
LiveBench 1.0 Data AnalysisLiveBench80.3%–
AA-Omniscience v1.1Artificial Analysis46.350
MMLU-ProVals AI92.4%–
LegalBenchVals AI88.5%–
TaxEvalVals AI76.0%–
PRBench FinanceScale AI SEAL50.8%†–
PRBench LegalScale AI SEAL51.6%†43.1%†
BioMysteryBenchVals AI–80.7%
Excel Modeling BenchmarkVals AI76.7%–
Excel Modeling Benchmark v1.1Vals AI76.7%76.0%
MedCodeVals AI53.5%–
MedScribeVals AI91.3%–
Public Benefits Bench v1.1Vals AI74.9%–
Financial Coaching BenchVals AI75.7%–
Immigration BenchVals AI75.4%–
DrugDiscoveryBenchScale AI SEAL–65.5%†
EBR-benchEpoch AI Benchmarking Hub57.1%92.4%
GDP.pdfEpoch AI Benchmarking Hub49.4%–
AA-Omniscience v1.1: accuracyArtificial Analysis68.4%68.6%
AA-Omniscience v1.1: non-hallucinationArtificial Analysis30.0%40.9%
HealthBench Professional (AA)OpenAI57.8%–
Instruction following
LiveBench LanguageLiveBench89.5%–
LiveBench Instruction FollowingLiveBench73.0%–
MultiChallengeScale AI SEAL–73.2%†
Arena Instruction FollowingArena (LMArena)1502–
Human preference
Arena TextArena (LMArena)1502–
EQ-Bench Creative Writing v3EQ-Bench2155†–
Arena Creative WritingArena (LMArena)1492–
Arena Multi-turnArena (LMArena)1484–
Arena Longer QueriesArena (LMArena)1510–
Multimodal
Arena VisionArena (LMArena)1322–
LiveBench DesignLiveBench81.6%82.8%
MMMU-ProArtificial Analysis–89.5%
MMMU-Pro (Vals)Vals AI90.6%–
MortgageTaxVals AI70.8%–
Humanity's Sixth SenseScale AI SEAL40.8%†63.2%†
GeoBenchGeoBench84.0%†–
Blueprint-Bench 2Epoch AI Benchmarking Hub41.9%†–
Furniture AssemblyEpoch AI Benchmarking Hub70.0%89.2%
VIALS-AAHandshake AI–65.8%
Code2Video-AAArtificial Analysis1325–
AA-3DArtificial Analysis11391318
Long context
AA-LCR v1.1Artificial Analysis85.3%–
Arena DocumentArena (LMArena)1498–
MLCRArtificial Analysis15.6%39.4%
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub167.1†174.2†
LiveBench 2.0LiveBench84.0%84.9%
LiveBench 1.0LiveBench83.4%–
AA Intelligence Index v5.0.1Artificial Analysis49.262.1
AA Intelligence Index v4.3.2Artificial Analysis53.4–
AA Progress Index v1Artificial Analysis340.8–
Vals IndexVals AI–67.7
Vals Finance IndexVals AI–57.3%
Vals RSI IndexVals AI36.1%29.0%
Vals Science IndexVals AI–68.4%
Vals Legal IndexVals AI–69.7%
AA Cyber IndexArtificial Analysis25.037.3
Safety & honesty
FORTRESSScale AI SEAL13.7%†–
DistressBenchScale AI SEAL71.5%†–

Data as of 2026-11-19. Best configuration of each model; every score links to its source on the model pages.

DuelLab GameBench 2, release gb2-20261114-ca113f475f5e (https://benchmarks.duellab.org/releases/gb2-20261114-ca113f475f5e/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.

What changed

  • GPT-6.2 Astra (max): BenchLeader Index 67.8 → 68.9.
  • Claude Fable 5.1 (max): 1 score revision.
  • GPT-6.2 Astra (max): 6 new results (VIALS-AA, Arena WebDev, Arena Agent…).
  • GPT-6.2 Astra (max): BenchLeader Index 67.2 → 67.8.
  • GPT-6.2 Astra (max): 2 new results (MKA (AA), Terminal-Bench).
  • Claude Fable 5.1 (max): 1 score revision.
  • Claude Fable 5.1 (max): 1 score revision.
  • Claude Fable 5.1 (max): 37 new results (LiveBench 2.0, LiveBench Long Agentic, LiveBench 2.0 Reasoning…).
  • Claude Fable 5.1 (max): 1 new result (GDPval-AA v2.1).
  • Claude Fable 5.1 (max): BenchLeader Index 67.1 → 66.6.

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

Claude Fable 5.1 vs GPT-6.2 Astra: questions

Is Claude Fable 5.1 better than GPT-6.2 Astra?
Claude Fable 5.1 (max) and GPT-6.2 Astra (max) are neck and neck on quality (66.4 vs 68.9, within the ±3.5 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 19 Nov 2026, so check the category scores for your use.
Claude Fable 5.1 vs GPT-6.2 Astra: which is cheaper, and will that change?
GPT-6.2 Astra is cheaper today: $16.00 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 GPT-6.2 Astra better for coding?
GPT-6.2 Astra scores higher in coding (76 vs 69 on the category index, where 50 is average). On Arena WebDev, the top shared coding benchmark, it is 1741 for Claude Fable 5.1 against 1781 for GPT-6.2 Astra.
Which is faster, Claude Fable 5.1 or GPT-6.2 Astra?
Claude Fable 5.1 streams ~1.5× faster (90 vs 49 output tokens per second, Artificial Analysis 7-day median).
Is Claude Fable 5.1 or GPT-6.2 Astra better for agents and tool use?
GPT-6.2 Astra scores higher in agentic tasks (66 vs 62 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 62.1% for GPT-6.2 Astra.
More questions (4)
Which is better for long documents?
Both take about 1.1M tokens: Claude Fable 5.1 1,000,000, GPT-6.2 Astra 1,050,000.
Which has lower latency?
Claude Fable 5.1 answers first: 140.2 s against 202.7 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 GPT-6.2 Astra?
Across the 53 benchmarks both have, Claude Fable 5.1 leads 11, GPT-6.2 Astra leads 41 and 1 is a tie. Every overall index that rates both puts GPT-6.2 Astra ahead.
When was GPT-6.2 Astra released?
GPT-6.2 Astra was released on 17 Nov 2026.