Benchmarks
More
OverviewBenchmaxxingCompareChartsCost vs CapabilityProviders per ModelProvider explorerGatewaysEU & SovereignJev-class modelsAbout
← All models

Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)

deprecated by benchmark source
Anthropic · released 2026-06-09 · 10 offers

Output 66 tokens/sFirst token 39 sContext 1M tokens

Top 5 cheapest providers (Adjusted $/task)

The same list price can give a different adjusted $/task (caching, token efficiency) — click a price for its inputs.

Within the active global provider, residency and confidentiality filters.

#ProviderAdjusted $/task
1Amazon Bedrock
2Google
3Azure
4Google Vertex AI
5T-Systems LLM Hub

Composite

7 of 7 inputs · 4 from the model family6 radar axes: DesignArena's two boards share one

95.8

AA CodingCoding Agent v1.4AA IntelligenceAA AgenticEpoch ECISoftware ECIDesignArenaAA Coding: percentile 94Coding Agent v1.4: percentile 95AA Intelligence: percentile 99Epoch ECI: percentile 95Software ECI: percentile 96DesignArena: percentile 78

AA Coding 76.5Coding Agent v1.4 67.2AA Intelligence 49.7AA Agentic —Epoch ECI 163.3Software ECI 165.8DesignArena 1274/1285

Radar: percentile among all models measured on each input; a gap means not measured.

Benchmark sheet

48 of 140 registered benchmark versions · bars show the percentile among all models measured on each benchmark.

Composite attachments (used in the score, not counted as exact benchmarks):
  • Epoch ECI · attached
  • Software ECI · attached
  • DesignArena Web Apps (agentic) · attached
  • DesignArena Full-Stack · attached
Compare this model →

Agentic

  • AA-AnalystAgent8448.8%

    AA-AnalystAgent published 2026-09-10 ↗ · Published board — Tests analyst tasks using agentic Python execution across fourteen domains.

  • AA-Briefcase921,530 Elo

    AA-Briefcase published 2026-09-10 ↗ · Published board — Tests multi-week professional knowledge-work projects with linked tasks and large source collections.

  • GDPval-AA v2941,631 Elo

    GDPval-AA v2 v2 ↗ · Published board — Tests professional knowledge-work deliverables across occupations using AA's Stirrup harness.

  • Harvey LAB-AA9593.6%

    Harvey LAB-AA published 2026-09-10 ↗ · Published board — Tests legal-work deliverables across practice areas on Harvey's private task set. Artificial Analysis' run, graded by one LLM judge against task rubrics — not the same run or scale as Vals AI's HLAB row.

  • Terminal-Bench Hard (AA)10062.9%

    Terminal-Bench Hard (AA) pinned revision 74221fb ↗ · Published board — Tests a pinned 44-task hard subset of terminal-based work using Terminus 2.

  • Terminal-Bench v2.1 (AA)8984.6%

    Terminal-Bench v2.1 (AA) v2.1 ↗ · Published board — Tests terminal-based work on the 89-task verified refresh using Terminus 2.

  • Terminal-Bench v4.0 (AA)9342.4%

    Terminal-Bench v4.0 (AA) v4.0 ↗ · Published board — Tests terminal-based work on the 66-task release using mini-SWE-agent v2.4.6.

  • Terminal-Bench v4.0no percentile42.0%

    Terminal-Bench v4.0 ↗ · Claude Code in --bare mode — A benchmark to measure and evolve with the frontier of agent work, whose homepage leaderboard reports resolution rate on Terminal-Bench 4.0 tasks.

  • ApprenticeBench CUA (NeoCognition)6234.0%

    ApprenticeBench CUA (NeoCognition) published 2026-09-14 ↗ · Claude Code — A computer-use agent operates the Odoo ERP through its screens across 100 sequential accounts-payable tasks with diminishing mentoring.

  • ApprenticeBench API (NeoCognition)8545.0%

    ApprenticeBench API (NeoCognition) published 2026-09-14 ↗ · Claude Code — An agent completes the same 100 sequential accounts-payable tasks in the Odoo ERP with diminishing mentoring, using dedicated application API calls instead of the screen interface.

  • Vals Index v2 (Vals AI)9066.0%

    Vals Index v2 (Vals AI) v2 ↗ · Published board — GDP-weighted average of agentic model performance across finance, coding and legal tasks.

  • Finance Agent v2 (Vals Index v2)7056.3%

    Finance Agent v2 (Vals Index v2) v2 ↗ · Published board — Multi-step financial reasoning tasks.

  • HLAB — Harvey's Legal Agent Benchmark (Vals Index v2)8011.3%

    HLAB — Harvey's Legal Agent Benchmark (Vals Index v2) v2 ↗ · Published board — Long-horizon legal work product creation. Vals AI's run of Harvey's Legal Agent Benchmark, reported as accuracy — not comparable with Artificial Analysis' Harvey LAB-AA row.

  • EBR-bench (Earthborne Rangers, Epoch AI)6939.5%

    EBR-bench (Earthborne Rangers, Epoch AI) published 2026-09-18 ↗ · Published board — Learning-capability test: models repeatedly play the obscure campaign board game Earthborne Rangers with note-taking, and the score measures whether results improve across playthroughs.

  • PostTrainBench v1.110041.8%

    PostTrainBench v1.1 ↗ · Claude Code — Agents retrain four small base models (gemma-3-4b-pt, SmolLM3-3B-Base, Qwen3-1.7B-Base, Qwen3-4B-Base) for each of 7 benchmark families; the leaderboard value is the weighted mean over base models × benchmarks, aggregated over the 2–3 listed runs per agent.

Coding

Efficiency

Instruction-following

Knowledge

Long-context

  • GDP.pdf (AA)8824.0%

    GDP.pdf (AA) published 2026-09-10 ↗ · Published board — Tests professional reasoning over long PDFs with AA document preparation and grading.

  • AA-LCR v1.19682.3%

    AA-LCR v1.1 v1.1 ↗ · Published board — Tests reasoning across multiple long documents with corrected answer keys and grading.

  • MLCR-AA9964.4%

    MLCR-AA published 2026-09-10 ↗ · Published board — Tests medical-record synthesis and reasoning across long, fragmented case documents.

Math

  • ArXivMath 06/2026 (MathArena) v2026-067085.4%

    ArXivMath 06/2026 (MathArena) v2026-06 ↗ · Published board — Research-level math problems with a checkable final answer, drawn from arXiv papers submitted in June 2026, so they postdate most training data.

  • BrokenArXiv 06/2026 (MathArena) v2026-065047.8%

    BrokenArXiv 06/2026 (MathArena) v2026-06 ↗ · Published board — Plausible but false proof statements taken from June 2026 arXiv papers; a model scores by refusing to prove them and saying the statement is false as written.

  • FrontierMath Tiers 1–3 v2 (Epoch AI)8887.0%

    FrontierMath Tiers 1–3 v2 (Epoch AI) v2 ↗ · Published board — Unpublished, expert-written mathematics problems from undergraduate to research level with automatically checkable answers, run by Epoch AI on its private v2 set.

  • FrontierMath Tier 4 v2 (Epoch AI)8890.2%

    FrontierMath Tier 4 v2 (Epoch AI) v2 ↗ · Published board — The hardest, research-level tier of Epoch AI's unpublished FrontierMath problems, run by Epoch AI on its private v2 set.

Reasoning

  • Chess Puzzles (Epoch AI)8041.0%

    Chess Puzzles (Epoch AI) published 2026-09-18 ↗ · Published board — Best-move selection on 100 novel chess positions generated programmatically by Epoch AI, each with a single Stockfish-verified best move; probes spatial reasoning and planning.

  • Mystery Game Puzzles (Epoch AI)8552.0%

    Mystery Game Puzzles (Epoch AI) published 2026-09-18 ↗ · Published board — Best-move selection on 100 mid-game positions of a well-known game whose identity Epoch deliberately keeps undisclosed, generated programmatically like Chess Puzzles.

  • AA Intelligence Index9949.7

    AA Intelligence Index published 2026-09-19 ↗ · Published board — Artificial Analysis publishes this board without a version number; we keep the date each result was retained.

Science

Tool-use

Unusual results

4 threshold-crossing signals flagged · 36 eligible benchmark families

How flags are calculated

Heuristic screen, not statistical significance: benchmark families are correlated and source uncertainty is unknown. Peer evidence needs ≥ 20 independently measured matched configurations from ≥ 10 distinct model families. A flag needs a directed population z-score of magnitude ≥ 1.5 and a gap of ≥ 1.5 from the leave-one-benchmark-family-out mean z in the same direction, over ≥ 5 other benchmark families.

  • unusually weak Vals Index v2 cost per test (Vals AI)
    Why
    Observed: 28.72507 USD
    Peer mean 7.03053 · peer sd 7.84824 · n 31 · families 30
    Directed z -2.764 · baseline z 1.408 · gap -4.172 · profile n 35
    28.72507 USDmeasuredobserved 2026-09-18vals.ai ↗
    Evidence
    Axis: Vals Index v2 cost per test (Vals AI) · v2 · Published board
    Exact value: 28.725071 USD
    Observed: 2026-09-18T13:00:43.826192+00:00 · publication date: not recorded
    Observation id: public:8ff5dba3134e2db88a520a2b
  • unusually strong CritPt (AA) published 2026-09-10
    Why
    Observed: 0.28571 fraction
    Peer mean 0.03928 · peer sd 0.07596 · n 522 · families 369
    Directed z 3.244 · baseline z 1.236 · gap 2.008 · profile n 35
    0.28571 fractionmeasuredobserved 2026-09-10artificialanalysis.ai ↗
    Evidence
    Axis: CritPt (AA) · published 2026-09-10 · Published board
    Exact value: 0.2857142857 fraction
    Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
    Observation id: aa:cd55210d-358e-4df1-ba9c-9acb5f186cc9:critpt
  • unusually strong AA Intelligence Index published 2026-09-19
    Why
    Observed: 49.7 points
    Peer mean 15.94317 · peer sd 11.48893 · n 644 · families 483
    Directed z 2.938 · baseline z 1.245 · gap 1.693 · profile n 35
    49.7 pointsmeasuredobserved 2026-09-19artificialanalysis.ai ↗
    Evidence
    Axis: AA Intelligence Index · published 2026-09-19 · Published board
    Exact value: 49.7 points
    Observed: 2026-09-19 · publication date: not recorded
    Observation id: legacy:aa_intelligence_index:claude-fable-5::max
    Protocol: inspect · file data/raw/artificialanalysis.json
  • unusually strong Humanity's Last Exam (AA text-only) published 2026-09-10
    Why
    Observed: 0.55468 fraction
    Peer mean 0.15283 · peer sd 0.14006 · n 608 · families 449
    Directed z 2.869 · baseline z 1.247 · gap 1.622 · profile n 35
    0.55468 fractionmeasuredobserved 2026-09-10artificialanalysis.ai ↗
    Evidence
    Axis: Humanity's Last Exam (AA text-only) · published 2026-09-10 · Published board
    Exact value: 0.554680259499537 fraction
    Observed: 2026-09-10T21:47:16.627Z · publication date: not recorded
    Observation id: aa:cd55210d-358e-4df1-ba9c-9acb5f186cc9:hle
Missing coverage · 95 benchmark versions

No result does not mean a zero, or that the model was never tested. Collection failures and disputed versions retain their distinct status.

Variants / reasoning settings

Artificial Analysis snapshot 2026-09-19 · Data: Artificial Analysis · Data: Epoch AI (CC BY)

VariantAA CodingAA Intelligence
Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)76.549.7
Claude Fable 5 (Adaptive Reasoning, Low Effort, Opus 4.8 Fallback)——
Claude Fable 5 (Adaptive Reasoning, Xhigh Effort, Opus 4.8 Fallback)——
Claude Fable 5 (Adaptive Reasoning, Medium Effort, Opus 4.8 Fallback)——
Claude Fable 5 (Adaptive Reasoning, High Effort, Opus 4.8 Fallback)——

SUBSCRIPTION PLAN

GitHub Copilot

Current usage-based billing · model token cost is converted to AI Credits at 1 credit = $0.01.

Input $10.00 / 1M
Cached input $1.00 / 1M
Cache write $12.50 / 1M
Output $50.00 / 1M
Status GA
Token offers by platform · 7 offers (Adjusted $/task)

Click any underlined price to see how it is estimated and where each input comes from. How we calculate adjusted cost.

7 offers within the active global filters; “—” means the catalog is active but no public token price is available.

OpenRouter (4)

Amazon Bedrock
Google
Azure
Google

Google Vertex AI (2)

Google Vertex AI
Google Vertex AI

T-Systems LLM Hub (1)

T-Systems LLM Hub
Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) — benchmarks & cost | Benchmark Heaven