AnthropicClaude Fable 5
Reasoning effort
Claude Fable 5 is an Anthropic proprietary reasoning model, released 9 Jun 2026. Its best configuration (max reasoning effort) ranks #11 of 775 on the BenchLeader Index at 69.4 ±4.4, in the top 25. The ± is the point: 52 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in composite (85) and lowest in instruction following (63). At $20.00 per million tokens blended it is among the most expensive ranked models. Output speed of 67 tokens per second puts it slower than most, with a first answer in 74.7 s. It has been measured at 7 reasoning-effort settings; this summary describes the best-scoring one, and the tabs above switch between them. Last measured 9 Jun 2026.
- Blended price
- $20.00/M
- $10.00 in · $50.00 out
- Output speed
- 67 tok/s
- measured by Artificial Analysis
- First answer
- 75 s
- first token 3.61 s
- Context
- 1M
- Full answer
- 82 s
- median, reasoning included
- Cost per run
- $8.75
- one full Intelligence Index run
- Released
- 9 Jun 2026
- Overall index69
- Reasoning74
- Coding74
- Agents & tools65
- Maths73
- Knowledge81
- Instruction following63
- Long context66
- Composite85
Versions
Anthropic has shipped 2 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.
| Model | Released | Index | Rank |
|---|---|---|---|
| Claude Fable 5.1max | 1 Sept 2026 | 70.6 | #5 |
| Claude Fable 5maxthis page | 9 Jun 2026 | 69.4 | #11 |
Reasoning-effort configurations
The same model behaves differently depending on how much it is allowed to think. Each row is one setting, scored only on the benchmarks that were run at that setting. “Not stated” collects results from publishers that did not say which setting they used; for a reasoning model that is usually its thinking mode, but we do not assume it. Pick a setting here or at the top of the page to see its price, speed and category scores.
| Effort | Index | Rank | Speed | First answer | Chat reply cost | Categories |
|---|---|---|---|---|---|---|
| low | – | – | 60 tok/s | 3.61 s | $0.019 | Maths 66 · Reasoning 62 |
| medium | – | – | 60 tok/s | 3.61 s | $0.019 | Reasoning 68 |
| high | 64.8 | #45 | 60 tok/s | 3.61 s | $0.019 | Agents & tools 65 · Coding 69 · Human preference 70 · Maths 70 · Multimodal 68 · Reasoning 67 |
| xhigh | – | – | 60 tok/s | 3.61 s | $0.019 | Knowledge 74 · Reasoning 70 |
| maxbest | 69.4 | #11 | 67 tok/s | 75 s | $0.019 | Agents & tools 65 · Coding 74 · Composite 85 · Instruction following 63 · Knowledge 81 · Long context 66 · Maths 73 · Reasoning 74 |
| thinking | – | – | 60 tok/s | 3.61 s | $0.019 | Reasoning 82 |
| not stated | 67.1 | #28 | 60 tok/s | 3.61 s | $0.019 | Agents & tools 65 · Coding 70 · Composite 68 · Human preference 71 · Knowledge 67 · Reasoning 80 |
How its index has moved
8 Sept 2026 to 20 Oct 2026- max
- not stated
- high
The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.
Benchmark results
See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | low | medium | high | xhigh | max | thinking | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|---|---|
| GPQA Diamond | 78.8%#131 | – | 83.3%#102 | – | 85.9%#83 | – | – | Epoch AI Benchmarking Hub | |
| SimpleBench | – | – | – | – | 81.9%#1 | – | – | SimpleBench | |
| Arena Hard Prompts | – | – | 1529#4 | – | – | – | – | Arena (LMArena) | |
| LiveBench 2.0 Reasoningnot in indexeffort not stated | – | – | – | – | – | – | 89.7%#14 | LiveBench | |
| LiveBench 1.0 Reasoningnot in index | – | – | – | – | 89.7%#15 | – | – | LiveBench | |
| GPQA Diamond (AA)not in index | – | – | – | – | 92.6%#32 | – | – | Artificial Analysis | |
| Humanity's Last Exam (AA)not in index | – | – | – | – | 55.5%#8 | – | – | Artificial Analysis | |
| GPQA Diamond (Vals)not in indexeffort not stated | – | – | – | – | – | – | 93.2%#10 | Vals AI | |
| EnigmaEval | – | – | 39.3%#1 | – | – | – | – | Scale AI SEAL | |
| Kagi LLM Benchmark | – | – | – | – | – | 91.4%#1 | 88.8%#2 | Kagi LLM Benchmark | |
| ARC-AGI-1 | 90.5%#68 | 92.5%#51 | 95.5%#31 | 98.5%#1 | 98.5%#1 | – | – | ARC Prize | |
| ARC-AGI-2 | 76.8%#44 | 82.5%#39 | 87.5%#23 | 88.3%#21 | 89.2%#18 | – | – | ARC Prize | |
| CritPt | – | – | – | – | 28.6%#24 | – | – | Artificial Analysis | |
| Chess Puzzlesnot in index | 31.0%#65 | – | 45.0%#28 | – | 47.0%#24 | – | – | Epoch AI Benchmarking Hub | |
| Mystery Game Puzzlesnot in index | – | – | – | – | 52.0%#11 | – | – | Epoch AI Benchmarking Hub | |
| LMCAnot in index | 59.6%#34 | 60.3%#33 | 61.1%#30 | 61.0%#31 | 60.3%#32 | – | – | Epoch AI Benchmarking Hub | |
| DTBenchnot in index | 91.5%#72 | 95.7%#35 | 96.5%#22 | 97.3%#9 | 98.4%#2 | – | – | Epoch AI Benchmarking Hub | |
| ForecastBenchnot in index | – | – | 65.7%#9 | – | 66.0%#7 | – | – | ForecastBench | |
| BTF-3not in index | – | – | 13.0%#12 | – | – | – | – | Epoch AI Benchmarking Hub |
Coding
| Benchmark | low | medium | high | xhigh | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|---|
| SciCode | – | – | – | – | 61.0%#5 | – | SciCode | |
| WeirdML | – | – | 87.8%#11 | – | 91.9%#6 | – | WeirdML | |
| FrontierCodeeffort not stated | – | – | – | – | – | 53.5%#2 | Cognition | |
| GSO-Bencheffort not stated | – | – | – | – | – | 78.4%#3 | GSO-Bench | |
| Arena Coding | – | – | 1551#2 | – | – | – | Arena (LMArena) | |
| Arena WebDev | – | – | 1624#21 | – | – | – | Arena (LMArena) | |
| LiveBench 2.0 Codingnot in indexeffort not stated | – | – | – | – | – | 98.3%#1 | LiveBench | |
| LiveBench 1.0 Codingnot in index | – | – | – | – | 86.0%#6 | – | LiveBench | |
| SciCode (AA)not in index | – | – | – | – | 61.0%#6 | – | Artificial Analysis | |
| LiveCodeBencheffort not stated | – | – | – | – | – | 89.8%#2 | Vals AI | |
| SWE-bench (Vals)not in indexeffort not stated | – | – | – | – | – | 95.0%#7 | Vals AI | |
| Code Migrationnot in indexeffort not stated | – | – | – | – | – | 55.1%#10 | Vals AI | |
| ProgramBenchnot in indexeffort not stated | – | – | – | – | – | 2.0%#10 | Vals AI | |
| Vibe Code Bench v1.1not in indexeffort not stated | – | – | – | – | – | 90.3%#4 | Vals AI | |
| SWE Atlas: Codebase QnAnot in index | – | – | – | 39.0%#12 | – | – | Scale AI SEAL | |
| SWE Atlas: Refactoringnot in index | – | – | – | 54.8%#3 | – | – | Scale AI SEAL | |
| SWE Atlas: Test Writingnot in index | – | – | – | 55.6%#3 | – | – | Scale AI SEAL | |
| MirrorCodenot in index | – | – | 63.9%#3 | – | – | – | Epoch AI Benchmarking Hub | |
| Surface Evolver Benchnot in index | – | – | 95.0%#1 | – | – | – | Epoch AI Benchmarking Hub | |
| DeepSWE v1.1not in index | 59.6%#33 | 65.4%#26 | 68.6%#18 | 69.9%#12 | 69.7%#13 | – | Epoch AI Benchmarking Hub | |
| ALE-Benchnot in index | – | – | 2041.3#9 | – | – | – | Epoch AI Benchmarking Hub | |
| FrontierSWEnot in index | – | – | – | – | 47.0%#7 | – | Epoch AI Benchmarking Hub | |
| Terminal-Bench 4.0 (AA)not in index | – | – | – | – | 42.4%#27 | – | Artificial Analysis | |
| Terminal-Bench 2.1 (AA)not in index | – | – | – | – | 84.6%#28 | – | Artificial Analysis | |
| Startrise Frontendnot in indexeffort not stated | – | – | – | – | – | 73.8%#11 | Startrise |
Agents & tools
| Benchmark | low | medium | high | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|
| Terminal-Bench | – | – | – | 44.5%#42 | – | Terminal-Bench | |
| Remote Labor Indexeffort not stated | – | – | – | – | 15.8%#4 | Scale AI / CAIS | |
| APEX-Agentseffort not stated | – | – | – | – | 63.6%#10 | Mercor | |
| Arena Agent | – | – | 8.4#8 | – | – | Arena (LMArena) | |
| LiveBench Long Agenticnot in indexeffort not stated | – | – | – | – | 53.2%#10 | LiveBench | |
| LiveBench Browsernot in indexeffort not stated | – | – | – | – | 92.0%#3 | LiveBench | |
| LiveBench Agentic Codingnot in index | – | – | – | 62.2%#10 | – | LiveBench | |
| Terminal-Bench Hard | – | – | – | 62.9%#2 | – | Artificial Analysis | |
| τ²-Bench Telecom (AA)not in index | – | – | – | 98.5%#4 | – | Artificial Analysis | |
| Terminal-Bench 2.1 (Vals)effort not stated | – | – | – | – | 80.5%#10 | Vals AI | |
| MCP Atlaseffort not stated | – | – | – | – | 83.3%#7 | Scale AI SEAL | |
| HiL-Bencheffort not stated | – | – | – | – | 56.3%#11 | Scale AI SEAL | |
| τ³-bench Bankingnot in index | – | – | – | 39.7%#8 | – | τ²-bench | |
| GDPval-AA v2.1not in index | – | – | – | 55.5%#29 | – | Artificial Analysis | |
| τ³-Banking (AA) | – | – | – | 38.1%#38 | – | Artificial Analysis | |
| Analyst Agent (AA)not in index | – | – | – | 48.8%#12 | – | Artificial Analysis | |
| Finance Agent v2not in indexeffort not stated | – | – | – | – | 56.3%#19 | Vals AI | |
| Legal Research Benchnot in indexeffort not stated | – | – | – | – | 49.5%#8 | Vals AI | |
| Tax Agent Benchnot in indexeffort not stated | – | – | – | – | 38.3%#10 | Vals AI | |
| Terminal-Bench 4.0 (Vals)not in indexeffort not stated | – | – | – | – | 41.4%#11 | Vals AI | |
| Terminal-Bench Sciencenot in indexeffort not stated | – | – | – | – | 15.7%#12 | Vals AI | |
| Web Search Indexnot in indexeffort not stated | – | – | – | – | 46.9%#2 | Vals AI | |
| Arena Searchnot in index | – | – | 1229#6 | – | – | Arena (LMArena) | |
| PostTrainBenchnot in index | – | – | – | 41.8%#1 | – | Epoch AI Benchmarking Hub | |
| GBAEvalnot in indexeffort not stated | – | – | – | – | 74.5%#2 | Epoch AI Benchmarking Hub | |
| Vending-Bench 2not in index | 5018.5#33 | 4339.8#39 | 5680.3#24 | 4966.6#35 | 4529.9#37 | Andon Labs | |
| AutomationBenchnot in index | – | – | – | 54.1%#61 | – | Artificial Analysis | |
| GDP.pdf (AA)not in index | – | – | – | 24.0%#37 | – | Artificial Analysis | |
| EnterpriseOps-Gymnot in index | – | – | – | 51.1%#1 | – | Artificial Analysis | |
| AA-Briefcase v1.1not in index | – | – | – | 1539#24 | – | Artificial Analysis |
Maths
| Benchmark | low | high | max | Source | Trend |
|---|---|---|---|---|---|
| FrontierMath Tiers 1–3 | – | – | 87.0%#9 | Epoch AI Benchmarking Hub | |
| FrontierMath Tier 4 | – | – | 90.2%#7 | Epoch AI Benchmarking Hub | |
| OTIS Mock AIME | 97.8%#30 | 100.0%#1 | 99.7%#13 | Epoch AI Benchmarking Hub | |
| ProofBench | – | – | 95.0%#8 | Vals AI | |
| LiveBench Mathematicsnot in index | – | – | 96.0%#12 | LiveBench | |
| Arena Maths | – | 1523#3 | – | Arena (LMArena) |
Knowledge
| Benchmark | xhigh | max | not stated | Source | Trend |
|---|---|---|---|---|---|
| SimpleQA Verified | 70.7%#7 | – | – | Epoch AI Benchmarking Hub | |
| LiveBench 2.0 Data Analysisnot in indexeffort not stated | – | – | 80.5%#7 | LiveBench | |
| LiveBench Researchnot in indexeffort not stated | – | – | 86.9%#3 | LiveBench | |
| LiveBench 1.0 Data Analysisnot in index | – | 80.5%#7 | – | LiveBench | |
| AA-Omniscience | – | 43.3#6 | – | Artificial Analysis | |
| MMLU-Proeffort not stated | – | – | 91.5%#3 | Vals AI | |
| LegalBencheffort not stated | – | – | 88.6%#1 | Vals AI | |
| CorpFineffort not stated | – | – | 71.8%#2 | Vals AI | |
| TaxEvaleffort not stated | – | – | 76.9%#5 | Vals AI | |
| PRBench Financeeffort not stated | – | – | 53.9%#4 | Scale AI SEAL | |
| PRBench Legaleffort not stated | – | – | 52.6%#5 | Scale AI SEAL | |
| Excel Modeling Benchmarknot in indexeffort not stated | – | – | 73.7%#5 | Vals AI | |
| MedCodenot in indexeffort not stated | – | – | 56.1%#4 | Vals AI | |
| MedScribenot in indexeffort not stated | – | – | 88.5%#12 | Vals AI | |
| Public Benefits Benchnot in indexeffort not stated | – | – | 70.4%#5 | Vals AI | |
| EBR-benchnot in index | – | 39.5%#10 | – | Epoch AI Benchmarking Hub | |
| GDP.pdfnot in index | – | 29.8%#9 | 30.0%#8 | Epoch AI Benchmarking Hub | |
| AA-Omniscience: accuracynot in index | – | 65.3%#5 | – | Artificial Analysis | |
| AA-Omniscience: non-hallucinationnot in index | – | 36.4%#180 | – | Artificial Analysis |
Instruction following
| Benchmark | high | max | Source | Trend |
|---|---|---|---|---|
| LiveBench Languagenot in index | – | 90.7%#1 | LiveBench | |
| LiveBench Instruction Followingnot in index | – | 75.8%#6 | LiveBench | |
| IFBench | – | 63.5%#113 | Artificial Analysis | |
| Arena Instruction Followingnot in index | 1508#4 | – | Arena (LMArena) |
Human preference
| Benchmark | high | not stated | Source | Trend |
|---|---|---|---|---|
| Arena Text | 1504#4 | – | Arena (LMArena) | |
| EQ-Bench 4effort not stated | – | 1340#2 | EQ-Bench | |
| Arena Creative Writingnot in index | 1501#3 | – | Arena (LMArena) | |
| Arena Multi-turnnot in index | 1518#3 | – | Arena (LMArena) | |
| Arena Longer Queriesnot in index | 1522#4 | – | Arena (LMArena) |
Multimodal
| Benchmark | high | not stated | Source | Trend |
|---|---|---|---|---|
| Arena Vision | 1325#1 | – | Arena (LMArena) | |
| LiveBench Designnot in indexeffort not stated | – | 84.7%#3 | LiveBench | |
| MMMU-Pro (Vals)not in indexeffort not stated | – | 89.3%#3 | Vals AI | |
| MortgageTaxnot in indexeffort not stated | – | 68.9%#8 | Vals AI | |
| SAGEnot in indexeffort not stated | – | 51.9%#9 | Vals AI | |
| Blueprint-Bench 2not in indexeffort not stated | – | 38.6%#6 | Epoch AI Benchmarking Hub |
Long context
| Benchmark | max | not stated | Source | Trend |
|---|---|---|---|---|
| AA-LCR | 82.3%#40 | – | Artificial Analysis | |
| Arena Documentnot in indexeffort not stated | – | 1499#1 | Arena (LMArena) | |
| MLCRnot in index | 64.4%#4 | – | Artificial Analysis |
Composite
| Benchmark | max | not stated | Source | Trend |
|---|---|---|---|---|
| Epoch Capabilities Indexnot in indexeffort not stated | – | 163.4#9 | Epoch AI Benchmarking Hub | |
| LiveBench 2.0effort not stated | – | 83.6%#6 | LiveBench | |
| LiveBench 1.0not in index | 83.0%#3 | – | LiveBench | |
| AA Intelligence Index v4.3.2 | 49.6#21 | – | Artificial Analysis | |
| Vals Multimodal Indexnot in indexeffort not stated | – | 74.2%#1 | Vals AI |
Where it wins
Benchmarks where this configuration ranks in the top five of every configuration measured.
Where to run it
Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.
| Provider | Speed | First token | Input $/M | Output $/M | Context | Quantisation |
|---|---|---|---|---|---|---|
| Google Vertex | 51 tok/s | 3.83 s | $10.00 | $50.00 | 1M | – |
| Anthropic | 49 tok/s | 3.62 s | $10.00 | $50.00 | 1M | – |
| Azure (BYOK Only) | 48 tok/s | 4.64 s | $10.00 | $50.00 | 1M | – |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache at $1.00 per 1M. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.019 | $0.016 | 1.3 min |
| Summarize a 30-page report | 12,000 / 600 | $0.150 | $0.069 | 1.4 min |
| Code edit | 6,000 / 1,500 | $0.135 | $0.095 | 1.6 min |
| Agentic coding session | 60,000 / 4,000 | $0.800 | $0.395 | 2.2 min |
| Structured extraction | 2,000 / 200 | $0.030 | $0.017 | 1.3 min |
More from Anthropic
Compare Claude Fable 5 with…
- Claude Fable 5 vs Claude Opus 5.5
- Claude Fable 5 vs Gemini 4 Argon
- Claude Fable 5 vs Muse Wonder Full
- Claude Fable 5 vs GPT-6 Astra
- Claude Fable 5 vs Claude Fable 5.1
- Claude Fable 5 vs GPT-6.1 Sol
- Claude Fable 5 vs Claude Sonnet 5.5
- Claude Fable 5 vs Claude Opus 5
- Claude Fable 5 vs GPT-5.6 Sol
- Claude Fable 5 vs Muse Wonder
- Claude Fable 5 vs Muse Spark 1.3
- Claude Fable 5 vs GPT-6 Sol
- Claude Fable 5 vs GPT-5.5
- Claude Fable 5 vs GPT-5.5 Pro
- Claude Fable 5 vs Kimi K3
- Claude Fable 5 vs GPT-5.4
- Claude Fable 5 vs Gemini 3.8 Flash
- Claude Fable 5 vs Muse Spark
- Claude Fable 5 vs GPT-5.6 Terra
- Claude Fable 5 vs MiMo-V2.6-Pro
- Claude Fable 5 vs Grok 4.6
- Claude Fable 5 vs Grok 4.7
- Claude Fable 5 vs GPT-5.3-Codex
- Claude Fable 5 vs GLM 5.3
- Claude Fable 5 vs Gemini 3.7 Flash
- Claude Fable 5 vs GPT-5.4 Pro
- Claude Fable 5 vs Claude Opus 4.7
- Claude Fable 5 vs Claude Opus 4.8
- Claude Fable 5 vs Qwen3.8 Max
- Claude Fable 5 vs Gemini 3.5 Flash
- Claude Fable 5 vs Muse Spark 1.2
- Claude Fable 5 vs Qwen3.8 2.4T A95B
- Claude Fable 5 vs DeepSeek V4.1 Flash 1017
- Claude Fable 5 vs Muse Spark 1.1
- Claude Fable 5 vs Claude Opus 4.6
- Claude Fable 5 vs GLM 5.3 Flash
- Claude Fable 5 vs DeepSeek V4 Pro
- Claude Fable 5 vs GLM 5.2
- Claude Fable 5 vs Qwen3.6 Max
- Claude Fable 5 vs Gemini 3.6 Flash
- Claude Fable 5 vs MiniMax-M3.1-Flash
- Claude Fable 5 vs Claude Haiku 5.5
- Claude Fable 5 vs Muse Spark Open
- Claude Fable 5 vs DeepSeek V4 Flash
- Claude Fable 5 vs Gemini 3.1 Pro
- Claude Fable 5 vs Qwen3 7
- Claude Fable 5 vs GPT-5.2
- Claude Fable 5 vs Step 5 Preview
- Claude Fable 5 vs Gemini 3 Pro
- Claude Fable 5 vs Claude Sonnet 5
- Claude Fable 5 vs Qwen3.8-Flash-Next
- Claude Fable 5 vs GPT-6 Luna
- Claude Fable 5 vs Claude Opus 4.5
- Claude Fable 5 vs GPT-5.6 Luna
- Claude Fable 5 vs MiMo-V2.6-Flash
- Claude Fable 5 vs GPT-5 Pro
- Claude Fable 5 vs o3
- Claude Fable 5 vs Kimi K2.6
- Claude Fable 5 vs GPT-5.2-Codex
See also
Data as of 21 Oct 2026. Compare these configurations.
Cite as: BenchLeader, “Claude Fable 5: benchmarks, pricing, speed and rank”, https://www.benchleader.com/models/claude-fable-5, data as of 21 Oct 2026.