Skip to main content

Model profile

Claude Fable 5

AnthropicCurrentReleased Jun 9, 2026
Data verified
Overall Score
82.76Public #3 of 215Verified #2 of 101
Arena Elo
1507
Eligible category ranks
3of 8
Price (1M tokens)
$10 in / $50 out
API pricing
Speed
Not listed
Context
1M+

Evidence coverage

34 of 369 tracked benchmarks are published. 12 are verified and 22 provisional. 6 of 8 categories are measured.

Updated July 24, 2026Methodology
Published / tracked
34 / 369
Verified
12
Provisional
22
Categories with evidence
6 / 8

Evidence by category

  • Agentic13 benchmarks
    Mixed evidence
  • Coding9 benchmarks
    Mixed evidence
  • Reasoning2 benchmarks
    Reported
  • Knowledge6 benchmarks
    Reported
  • Math0 benchmarks
    Not measured
  • Multilingual0 benchmarks
    Not measured
  • Multimodal3 benchmarks
    Mixed evidence
  • Inst. Following1 benchmark
    Reported
ProprietaryReasoning
Confidence:
Medium
base

Claude Fable 5 ranks #3 out of 215 models on the public leaderboard with an overall score of 82.76/100. It also ranks #2 out of 101 on the verified leaderboard. This places it among the top tier of AI models available in 2026, competing directly with the strongest models from leading AI labs.

Claude Fable 5 is a proprietary model with a 1M+ token context window. It uses explicit chain-of-thought reasoning, which typically improves performance on math and complex reasoning tasks at the cost of higher latency and token usage.

Claude Fable 5 is Anthropic's generally available Mythos-class model. It uses the same underlying model as Claude Mythos 5, with production safeguards for cybersecurity, biology, chemistry, distillation, and frontier-AI-development requests. Some Claude clients route flagged requests to Claude Opus 4.8; the Messages API blocks by default unless fallback is configured.

This profile currently has 34 of 369 tracked benchmarks. BenchLM only exposes non-generated benchmark rows publicly, so missing categories stay blank until a sourced evaluation is available.

Its strongest category is Coding (#2), while its weakest is Knowledge (#25). This performance profile makes it particularly well-suited for software development and code generation tasks.

Peer position

Exact provisional scores and ranks for the closest listed peers. A score can appear before a model clears the evidence threshold for a rank, so equal scores can have different rank states.

Range 76.685.88

  1. Claude Opus 5
    Anthropic
    #185.88
    Claude Opus 5 is #1 with a score of 85.88.
    Compare
  2. Claude Mythos 5
    Anthropic
    #283.01
    Claude Mythos 5 is #2 with a score of 83.01.
    Compare
  3. Claude Fable 5Current model
    Anthropic
    #382.76
    Claude Fable 5 is #3 with a score of 82.76.
  4. GPT-5.6 Sol
    OpenAI
    #481.46
    GPT-5.6 Sol is #4 with a score of 81.46.
    Compare
  5. Kimi K3
    Moonshot AI
    #579.98
    Kimi K3 is #5 with a score of 79.98.
    Compare
  6. Claude Opus 4.8
    Anthropic
    #677.44
    Claude Opus 4.8 is #6 with a score of 77.44.
    Compare
  7. Muse Spark 1.1
    Meta
    #776.6
    Muse Spark 1.1 is #7 with a score of 76.6.
    Compare

Category percentile

More

Relative position among models eligible for each sourced category. A higher percentile means a stronger position within that category's ranked cohort; 100 is highest.

  1. Coding99%
    Eligible cohort rank #2 of 130Category score 79.5
  2. Agentic95%
    Eligible cohort rank #8 of 129Category score 65.4
  3. Knowledge54%
    Eligible cohort rank #25 of 53Category score 69.2

Category evidence

Scores and ranks appear only where this model has published benchmark evidence. Categories without displayable source records remain not measured.

Category scores, ranks, weighting, benchmark coverage, and evidence status
CategoryScore
AgenticRank #8 of 129Percentile 95thWeight 22%13 benchmarksMixed sources65.4
CodingRank #2 of 130Percentile 99thWeight 20%9 benchmarksMixed sources79.5
ReasoningWeight 17%2 benchmarksReportedScore pending
KnowledgeRank #25 of 53Percentile 54thWeight 12%6 benchmarksReported69.2
MathWeight 5%0 benchmarksNot measuredNot measured
MultilingualWeight 7%0 benchmarksNot measuredNot measured
MultimodalRank Not rankedWeight 12%3 benchmarksMixed sources64.0
Inst. FollowingRank Not rankedWeight 5%1 benchmarkReported80.3

Chatbot Arena performance

Scroll horizontally to inspect confidence intervals and vote counts.

Chatbot Arena Elo, confidence interval, and vote count by evaluation view
ViewEloConfidence intervalVotes
Text Overall1507±6.414,646
Coding1553±10.03,992
Math1543±21.3761
Instruction Following1513±9.15,041
Creative Writing1508±12.22,721
Multi-turn1518±12.62,461
Hard Prompts1534±7.39,527
Hard Prompts (English)1532±9.54,470
Longer Query1522±8.66,403

Benchmark Details

Rows below have a displayable published verification record. Each source link and provenance note remains in the page HTML while its category is closed. Source-unverified manual rows and generated rows stay hidden.

Agentic13 benchmarks
Terminal-Bench 2.0Provider exact
84.3%Weighted 38%
Source: Anthropic: Claude Fable 5 and Claude Mythos 5 system cardProvenance: Table 8.1.A reports Fable 5 at 84.3% on Terminal-Bench 2.1. BenchLM maps this into the existing Terminal-Bench 2 slot until a separate 2.1 key exists.
OSWorld-VerifiedProvider exact
85%Weighted 34%
Source: Anthropic: Claude Fable 5 and Claude Mythos 5 system cardProvenance: Table 8.1.A reports Fable 5 at 85.0% on OSWorld-Verified.
GDPval-AAProvider exact
1747Display only
Source: Anthropic: Claude Fable 5 and Claude Mythos 5 system cardProvenance: Table 8.1.A reports Fable 5 at 1932 Elo on GDPval-AA as of June 6, 2026.
AA Agentic IndexReported

Artificial Analysis Agentic Index

52.8%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
τ²-bench resultsReported

τ²-Bench Tool-Agent-User Evaluation

98.5%Display only
Source: Artificial Analysis: tau2-bench leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
GDPval-AAReported

GDPval-AA normalized

62.3%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA BriefcaseReported

Artificial Analysis Briefcase

1574Display only
Source: Artificial Analysis: aa-briefcase leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA AutomationBenchReported

Artificial Analysis AutomationBench

48.6%Display only
Source: Artificial Analysis: automationbench-aa leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA EnterpriseOps-GymReported

Artificial Analysis EnterpriseOps-Gym

51.1%Display only
Source: Artificial Analysis: enterprise-ops-gym-aa leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA Harvey LABReported

Artificial Analysis Harvey LAB-AA

93.6%Display only
Source: Artificial Analysis: harvey-lab-aa leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA Tau3 BankingReported

Artificial Analysis Tau3-Banking

26.8%Display only
Source: Artificial Analysis: tau3-banking leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
terminalBenchHardReported
62.9%Display only
Source: Artificial Analysis: terminalbench-hard leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
aaTerminalBench21Reported
84.6%Display only
Source: Artificial Analysis: terminalbench-v2-1 leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
Coding9 benchmarks
SWE-bench VerifiedProvider exact

Software Engineering Benchmark Verified

95%Weighted 16%
Source: Anthropic: Claude Fable 5 and Claude Mythos 5 system cardProvenance: Section 8.2 reports Fable 5 at 95.0% on SWE-bench Verified, averaged over 5 trials.
SWE-bench ProProvider exact
80%Weighted 10%
Source: Anthropic: Claude Fable 5 and Claude Mythos 5 system cardProvenance: Section 8.2 reports Fable 5 at 80.0% on SWE-bench Pro, averaged over 5 trials.
FrontierCode 1.1 MainBenchmark exact
53.5%Display only
Source: Cognition: FrontierCode 1.1Provenance: Cognition reports Claude Fable 5 at 53.5% on FrontierCode 1.1 Main, using the best xhigh effort row from the published data JSON.
Terminal-Bench 2.0Provider exact
84.3%Display only
Source: Anthropic: Claude Fable 5 and Claude Mythos 5 system cardProvenance: Table 8.1.A reports Fable 5 at 84.3% on Terminal-Bench 2.1. BenchLM stores this in the existing Terminal-Bench display key.
cursorBench31Benchmark exact
70.6%Display only
Source: Cursor evals: CursorBench 3.1Provenance: Cursor reports Fable 5 High at this exact CursorBench 3.1 score on its public evals page. BenchLM stores it on the Claude Fable 5 row as a display-only coding-agent benchmark.
cursorBench32Benchmark exact
70.5%Display only
Source: Cursor evals: CursorBench 3.2Provenance: Cursor reports Fable 5 Max at this exact CursorBench 3.2 score on its public evals page. BenchLM stores it on the Claude Fable 5 row as a display-only coding-agent benchmark.
VulcanBench v3Benchmark exact
87.0%Display only
Source: VulcanBench v3 Technical Report No. 4Provenance: VulcanBench v3 reports Claude Fable 5 at 87.0% pass@1 at both low and high effort. We store the lower-cost low-effort row; six safety-classifier refusals in the full matrix used the report's Opus 4.8 fallback.
AA Coding IndexReported

Artificial Analysis Coding Index

76.5%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-SciCodeReported

Artificial Analysis SciCode

60.2%Display only
Source: Artificial Analysis: scicode leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
Reasoning2 benchmarks
AA-LCRReported

Artificial Analysis Long Context Reasoning

70.0%Display only
Source: Artificial Analysis: artificial-analysis-long-context-reasoning leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
CritPtReported

Critical Physics Tasks

28.6%Display only
Source: Artificial Analysis: critpt leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
Knowledge6 benchmarks
Artificial Analysis Intelligence IndexReported
59.9%Display only
Source: Artificial Analysis: artificial-analysis-intelligence-index leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA-GPQA DiamondReported

Artificial Analysis GPQA Diamond

92.6%Display only
Source: Artificial Analysis: gpqa-diamond leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA-HLEReported

Artificial Analysis Humanity's Last Exam

53.3%Display only
Source: Artificial Analysis: humanitys-last-exam leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA-Omniscience IndexReported

Artificial Analysis Omniscience Index

40.2%Display only
Source: Artificial Analysis: omniscience leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.
AA-Omniscience AccuracyReported

Artificial Analysis Omniscience Accuracy

61.4%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-Omniscience Hallucination RateReported

Artificial Analysis Omniscience Hallucination Rate

54.9%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Multimodal3 benchmarks
OfficeQA ProProvider exact
57.9%Weighted 30%
Source: Anthropic: Claude Fable 5 and Claude Mythos 5 system cardProvenance: Section 8.17.1 reports Fable 5 at 57.9% on Databricks' OfficeQA Pro evaluation.
Blueprint-Bench 2Provider exact
38.6%Display only
Source: Anthropic: Claude Fable 5 and Claude Mythos 5 system cardProvenance: Section 8.16.2 reports Fable 5 at 38.6% on Blueprint-Bench 2 using Andon Labs' standard format and harness.
Design Arena WebsiteReported

Design Arena Website Elo

1332Display only
Source: OpenRouter model benchmarksProvenance: Display-only Design Arena Website Elo synced from OpenRouter model benchmark metadata. It is excluded from BenchLM weighted scoring.
Inst. Following1 benchmark
AA-IFBenchReported

Artificial Analysis IFBench

63.5%Display only
Source: Artificial Analysis: ifbench leaderboardProvenance: Display-only row synced from the current Artificial Analysis evaluation leaderboard. It is excluded from BenchLM weighted scoring.

Frequently Asked Questions

How does Claude Fable 5 perform overall in AI benchmarks?

Claude Fable 5 currently ranks #3 out of 215 models on BenchLM's provisional leaderboard with an overall score of 82.76. It also ranks #2 out of 101 on the verified leaderboard. It is created by Anthropic. Its published context window is 1M+.

Is Claude Fable 5 good for knowledge and understanding?

Claude Fable 5 ranks #25 out of 53 models in knowledge and understanding benchmarks with an average score of 69.2. There are stronger options in this category.

Is Claude Fable 5 good for coding and programming?

Claude Fable 5 ranks #2 out of 130 models in coding and programming benchmarks with an average score of 79.5. It is among the top performers in this category.

Is Claude Fable 5 good for reasoning and logic?

Claude Fable 5 has visible benchmark coverage in reasoning and logic, but BenchLM does not currently assign it a global category rank there.

Is Claude Fable 5 good for agentic tool use and computer tasks?

Claude Fable 5 ranks #8 out of 129 models in agentic tool use and computer tasks benchmarks with an average score of 65.4. It is among the top performers in this category.

Is Claude Fable 5 good for multimodal and grounded tasks?

Claude Fable 5 has visible benchmark coverage in multimodal and grounded tasks, but BenchLM does not currently assign it a global category rank there.

Is Claude Fable 5 good for instruction following?

Claude Fable 5 has visible benchmark coverage in instruction following, but BenchLM does not currently assign it a global category rank there.

Does Claude Fable 5 have full benchmark coverage on BenchLM?

Not yet. Claude Fable 5 currently has 34 published benchmark scores out of the 369 benchmarks BenchLM tracks. BenchLM only exposes non-generated public benchmark rows, so missing categories stay blank until a sourced evaluation is available.

What is the context window size of Claude Fable 5?

Claude Fable 5 has a published context window of 1M+, which determines how much text it can process in a single interaction.

Last updated: July 24, 2026 · Runtime metrics stay blank until BenchLM has a sourced snapshot.