Models / Claude Fable 5

Anthropic

Claude Fable 5

Claude Fable 5 is best for writing, and reasoning and knowledge; pick it when quality matters more than cost. The cheapest model of similar intelligence is MiMo-V2.6-Pro, at $0.54 per million tokens against $20.00.

Superseded. Claude Fable 5.2 is Anthropic's newer model in this line, at $16.00 blended: see Claude Fable 5.2.

Results 16 Nov 2026 · 58 results · 10 sources

Price per million tokens
$10.00 in · $50.00 out
Anthropic's list price, 10 Nov 2026 · compare prices$1.00 cached input · 50% off in batch
Speed
Not measured
Intelligence Index
49.6
Artificial Analysis, at max reasoning
Spring Prompt overall
Not ranked yet
needs our benchmarks and two groups of results
Developer
Anthropic, based in the US
Weights not published
Released
9 Jun 2026
1,000,000 tokens of context

Where it stands among the models you could choose

Available models grouped by price, intelligence, speed and developer location. Retired models are excluded.

AmongIntelligence IndexSpring Prompt overallPrice, blendedSpeed
Models available today 9th of 185Claude Opus 5.5 – $20.00 blended, 98th percentilecheapest: Mistral Nemo –
Models priced $10 or more per million tokens 4th of 11Claude Fable 5.1 – sets this group –
Models with similar intelligence sets this group – $20.00 blended, 82nd percentilecheapest: MiMo-V2.6-Pro –
Models from developers based in the US 9th of 92Claude Opus 5.5 – $20.00 blended, 95th percentilecheapest: Gemma 3 4B –

The name under each rank is the leader of that group; green is the top quarter of the group and red the bottom quarter, by rank. Price is shown as a percentile: the share of the group that costs less, so lower is cheaper. "Sets this group" marks the measure the group is defined by. Spring Prompt overall is our score out of 100 across every source (how it works). Price is the developer's list price (or the typical OpenRouter host where we haven't read one) for three input tokens to one output; intelligence and speed are from Artificial Analysis (data sourced from Artificial Analysis); "similar intelligence" means within 4 points on its Intelligence Index. Developer locations are where each company is based, not where a model is served. Groups under 3 models are not ranked.

How good is it, and for what?

Each use case ranks the available models its benchmarks measured, then those priced $10 or more per million tokens. The bar shows its percentile in that field, best to the right. Open a row for the results behind it.

Product listingsTurning a sparse product feed and photos into listings that can go live Not measured
  • CatalogBench: has not measured this model.
Decks from an analysisTurning a finished analysis into a deck you could present as it is Not measured
  • DeckBench: has not measured this model.
User surveysPlanning a user survey and reading its results without being misled Not measured
  • SurveyBench: has not measured this model.
Marketing planningPlanning a year of ad spend without overspending Not measured
  • ROASBench: has not measured this model.
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 22nd of 159 available · 5th of 9 at its price
BenchmarkClaude Fable 5Rank among availableBest available
OpenHands IndexOpenHands Index: average · reported 81.0% 1st of 31 This model
Artificial AnalysisArtificial Analysis: Terminal-Bench 4.0 · reported 42.4% 12th of 107 Kimi K3.1 Pro 67.2%
Artificial AnalysisArtificial Analysis: Terminal-Bench 2.1 · reported 84.6% 12th of 107 Claude Fable 5.1 91.4%
Artificial AnalysisArtificial Analysis: τ-bench banking · reported 38.1% 21st of 104 Grok 4.6 50.7%
Vending-Bench 2Vending-Bench 2: money after a year · reported $5,680 19th of 53 GPT-6 Astra $15,515
  • tau2-bench: pending. Its latest results are dated 26 May 2026, before this model was released.
  • Berkeley Function Calling Leaderboard (BFCL) V4: pending. Its latest results are dated 16 Dec 2025, before this model was released.
  • Microsoft STATE-Bench: pending. Its latest results are dated 29 May 2026, before this model was released.
Professional workReal tasks from banking, consulting and law, business documents and freelance projects 6th of 51 available · 3rd of 9 at its price
BenchmarkClaude Fable 5Rank among availableBest available
APEX-AgentsAPEX-Agents: tasks passed · reported 63.6% 9th of 37 Claude Sonnet 5.5 75.5%
GDP.pdfGDP.pdf: professional document tasks · reported 30.0% 3rd of 31 GPT-5.6 Sol 30.7%
Remote Labor IndexRemote Labor Index: projects done to client standard · reported 16.1% 3rd of 12 GPT-6 Astra 20.8%
Reasoning and knowledgeHard questions across science, maths and general knowledge 12th of 187 available · 4th of 11 at its price
BenchmarkClaude Fable 5Rank among availableBest available
Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported 49.6 9th of 185 Claude Opus 5.5 57.6
Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported 55.5% 4th of 186 Claude Opus 5.5 61.4%
Artificial AnalysisArtificial Analysis: GPQA Diamond · reported 92.6% 18th of 168 GPT-6 Astra 96.3%
WritingWhat people prefer in blind comparisons, and judged writing quality 2nd of 169 available · 1st of 10 at its price
BenchmarkClaude Fable 5Rank among availableBest available
Arena (formerly LMArena)Arena Text: overall · reported 1,504 3rd of 153 Gemini 4 Argon 1,525
UGI LeaderboardUGI: writing score · reported 74.2 3rd of 124 Gemini 3.8 Flash 78.6
Sticking to the factsSummarising without inventing things, and factual answers 7th of 139 available · 2nd of 12 at its price
BenchmarkClaude Fable 5Rank among availableBest available
Arena (formerly LMArena)Arena Text factuality: overall · reported 1,484 8th of 109 Gemini 4 Argon 1,511
SimpleQA Verified (Epoch AI)SimpleQA Verified: correct answers · reported 70.7% 6th of 68 GPT-6 Astra 75.6%
  • Vectara Hallucination Leaderboard: has not measured this model.
Speed under pressureGood decisions against a real clock (fast chess) Not measured
  • BulletBench: has not measured this model.

Nearest alternatives

Against Claude Fable 5 at $20.00 blended, Intelligence Index 49.6. "Similar intelligence" means within 4 points or better.

Where to run it

6 hosts on OpenRouter at the standard service tier, with a median of $20.00 blended per million tokens. Cheapest first.

HostQuantisationInputOutputBlended
Amazon Bedrocknot stated$10.00$50.00$20.00
Anthropicnot stated$10.00$50.00$20.00
Azurenot stated$10.00$50.00$20.00
Claude Platform on AWSnot stated$10.00$50.00$20.00
Googlenot stated$10.00$50.00$20.00
Googlenot stated$11.00$55.00$22.00

Prices per million tokens from OpenRouter's public endpoint list, checked 10 Nov 2026.

Against the alternatives

The models you would most likely weigh it against: the leaders of the groups above.

Scroll sideways to see every alternative.

Claude Fable 5Claude Fable 5.1
most intelligent at $10 or more per million tokens
MiMo-V2.6-Pro
cheapest with similar intelligence
Claude Opus 5.5
most intelligent available today
Price per million tokens $20.00 $20.00$0.54$8.00
Tokens a second – 724396
Intelligence Index 49.6 53.446.357.6
Spring Prompt overall – 64–82
Rank among available models, by use case
Product listings – 24th–13th
Decks from an analysis – 11th–7th
User surveys – ––4th
Marketing planning – 10th–9th
Agents and tool use 22nd of 159 19th23rd3rd
Professional work 6th of 51 4th–3rd
Reasoning and knowledge 12th of 187 5th13th1st
Writing 2nd of 169 19th23rd5th
Sticking to the facts 7th of 139 5th10th3rd
Speed under pressure – –––

Shaded figures are better than Claude Fable 5's. A dash means no result.

Research and examples

Where it has been measured

4th most intelligent of the 11 models priced $10 or more per million tokens. Among models available today, in the top quarter (by percentile) for 5 of the 5 use cases measured, led by writing, and reasoning and knowledge.

Artificial Analysis lists it but has not published a speed for it yet

Every result

58 published results from 10 sources, each in the source's own units, with the configuration that produced it.

APEX-Agents · reported by APEX-Agents · 1 result
MeasureValueRankConfigurationDated
APEX-Agents: tasks passed% of tasks, higher is better 63.6% 9 of 39 Claude Fable 5 1 Oct 2026

Not shown: Not your firm's documents or tools; graded by rubric, not by a client.

Arena (formerly LMArena) · reported by Arena (formerly LMArena) · 13 results
MeasureValueRankConfigurationDated
Arena Agent: confirmed task successIPS effect estimate, higher is better 0.06
0.03–0.09
13 of 50 Claude Fable 5 (high reasoning, arena agent) 2 Oct 2026
Arena Agent: praise over complaintIPS effect estimate, higher is better 0.17
0.13–0.22
9 of 50 Claude Fable 5 (high reasoning, arena agent) 2 Oct 2026
Arena Agent: steerabilityIPS effect estimate, higher is better 0.09
0.08–0.10
5 of 50 Claude Fable 5 (high reasoning, arena agent) 2 Oct 2026
Arena Agent: tool groundingIPS effect estimate, higher is better 0.00
0.00–0.01
3 of 50 Claude Fable 5 (high reasoning, arena agent) 2 Oct 2026
Arena Document: overallArena rating, higher is better 1,499
1,491–1,507
1 of 44 Claude Fable 5 13 Sep 2026
Arena Search: overallArena rating, higher is better 1,229
1,221–1,237
2 of 34 Claude Fable 5 (arena search) 24 Aug 2026
Arena Text factuality: overallArena rating, higher is better 1,484
1,480–1,487
9 of 182 Claude Fable 5 (high reasoning) 2 Oct 2026
Arena Text: business, management and financeArena rating, higher is better 1,502
1,495–1,510
5 of 406 Claude Fable 5 (high reasoning) 2 Oct 2026
Arena Text: creative writingArena rating, higher is better 1,503
1,495–1,510
3 of 411 Claude Fable 5 (high reasoning) 2 Oct 2026
Arena Text: expert promptsArena rating, higher is better 1,549
1,540–1,559
2 of 363 Claude Fable 5 (high reasoning) 2 Oct 2026
Arena Text: instruction followingArena rating, higher is better 1,509
1,503–1,515
4 of 413 Claude Fable 5 (high reasoning) 2 Oct 2026
Arena Text: overallArena rating, higher is better 1,504
1,500–1,509
3 of 413 Claude Fable 5 (high reasoning) 2 Oct 2026
Arena Text: writing, literature and languageArena rating, higher is better 1,508
1,501–1,514
3 of 412 Claude Fable 5 (high reasoning) 2 Oct 2026

Not shown: Not a success rate: the estimated effect of choosing this model as the agent's orchestrator, against an even mix of the models tested, inside Arena's own harness.

Artificial Analysis · reported by Artificial Analysis · 12 results
MeasureValueRankConfigurationDated
Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better 76.5 15 of 187 Claude Fable 5 (max reasoning) 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 49.6 20 of 413 Claude Fable 5 (max reasoning) 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 92.6% 33 of 360 Claude Fable 5 (max reasoning) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 55.5% 8 of 419 Claude Fable 5 (max reasoning) 20 Oct 2026
Artificial Analysis: IFBench% of instructions, higher is better 63.5% 96 of 288 Claude Fable 5 (max reasoning) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 82.3% 37 of 407 Claude Fable 5 (max reasoning) 20 Oct 2026
Artificial Analysis: SciCode% of problems, higher is better 61.0% 5 of 205 Claude Fable 5 (max reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better 84.6% 28 of 188 Claude Fable 5 (max reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better 42.4% 29 of 204 Claude Fable 5 (max reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better 62.9% 2 of 282 Claude Fable 5 (max reasoning) 20 Oct 2026
Artificial Analysis: τ-bench banking% of tasks, higher is better 38.1% 38 of 175 Claude Fable 5 (max reasoning) 20 Oct 2026
Artificial Analysis: τ²-bench telecom% of tasks, higher is better 98.5% 3 of 286 Claude Fable 5 (max reasoning) 20 Oct 2026

Not shown: Not your codebase or tools.

GDP.pdf · reported by GDP.pdf · 2 results
MeasureValueRankConfigurationDated
GDP.pdf: professional document tasks% of rubric, higher is better 30.0% 4 of 49 Claude Fable 5 6 Jun 2026
GDP.pdf: professional document tasks% of rubric, higher is better 29.8% 5 of 49 Claude Fable 5 (max reasoning) 1 Oct 2026

Not shown: Not your documents; 100 tasks, so small differences are noise.

OpenHands Index · reported by OpenHands Index · 6 results
MeasureValueRankConfigurationDated
OpenHands Index: average% resolved, higher is better 81.0% 1 of 34 Claude Fable 5 (openhands) 30 Jun 2026
OpenHands Index: front end (SWE-Bench Multimodal)% resolved, higher is better 70.6% 1 of 34 Claude Fable 5 (openhands) 30 Jun 2026
OpenHands Index: greenfield (Commit0)% resolved, higher is better 62.5% 1 of 34 Claude Fable 5 (openhands) 30 Jun 2026
OpenHands Index: information gathering (GAIA)% resolved, higher is better 84.2% 2 of 34 Claude Fable 5 (openhands) 30 Jun 2026
OpenHands Index: issue resolution (SWE-Bench)% resolved, higher is better 95.8% 1 of 34 Claude Fable 5 (openhands) 30 Jun 2026
OpenHands Index: testing (SWT-Bench)% resolved, higher is better 91.9% 1 of 34 Claude Fable 5 (openhands) 30 Jun 2026

Not shown: Not the model alone: the score is for the model inside the OpenHands agent, at the SDK version shown.

Remote Labor Index · reported by Remote Labor Index · 1 result
MeasureValueRankConfigurationDated
Remote Labor Index: projects done to client standard% of projects, higher is better 16.1% 3 of 14 Claude Fable 5 1 Oct 2026

Not shown: Not speed or cost; a small set of projects, so a few points either way are noise.

SimpleQA Verified (Epoch AI) · reported by SimpleQA Verified (Epoch AI) · 1 result
MeasureValueRankConfigurationDated
SimpleQA Verified: correct answers% of questions, higher is better 70.7% 6 of 85 Claude Fable 5 (xhigh reasoning) 10 Aug 2026

Not shown: Not answers grounded in your documents; tests what the model remembers.

tau2-bench · reported by tau2-bench · 2 results
MeasureValueRankConfigurationDated
tau2 v1.0.1, banking knowledge, alltools retrieval: consistency (pass^4)% of tasks, higher is better 28.9% 5 of 21 Claude Fable 5 (max reasoning, tau2) 23 Jul 2026
tau2 v1.0.1, banking knowledge, alltools retrieval: task success (pass^1)% of tasks, higher is better 39.7% 8 of 21 Claude Fable 5 (max reasoning, tau2) 23 Jul 2026

Not shown: Not your policies or customers: the tasks and policies are tau2's own, and the customer is simulated by gpt-5.2.

UGI Leaderboard · reported by UGI Leaderboard · 15 results
MeasureValueRankConfigurationDated
UGI: requested-length error% off the requested word count, lower is better 2.0% 10 of 379 Claude Fable 5 (high reasoning) 10 Jun 2026
UGI: requested-length error% off the requested word count, lower is better 2.0% 10 of 379 Claude Fable 5 (low reasoning) 10 Jun 2026
UGI: requested-length error% off the requested word count, lower is better 2.0% 10 of 379 Claude Fable 5 (max reasoning) 10 Jun 2026
UGI: requested-length error% off the requested word count, lower is better 2.0% 10 of 379 Claude Fable 5 (medium reasoning) 10 Jun 2026
UGI: requested-length error% off the requested word count, lower is better 2.0% 10 of 379 Claude Fable 5 (xhigh reasoning) 10 Jun 2026
UGI: style adherencescore from 0 to 1, higher is better 0.40 30 of 379 Claude Fable 5 (high reasoning) 10 Jun 2026
UGI: style adherencescore from 0 to 1, higher is better 0.39 41 of 379 Claude Fable 5 (low reasoning) 10 Jun 2026
UGI: style adherencescore from 0 to 1, higher is better 0.38 75 of 379 Claude Fable 5 (max reasoning) 10 Jun 2026
UGI: style adherencescore from 0 to 1, higher is better 0.38 56 of 379 Claude Fable 5 (medium reasoning) 10 Jun 2026
UGI: style adherencescore from 0 to 1, higher is better 0.41 17 of 379 Claude Fable 5 (xhigh reasoning) 10 Jun 2026
UGI: writing scorescore out of 100, higher is better 74.2 5 of 379 Claude Fable 5 (high reasoning) 10 Jun 2026
UGI: writing scorescore out of 100, higher is better 71.9 14 of 379 Claude Fable 5 (low reasoning) 10 Jun 2026
UGI: writing scorescore out of 100, higher is better 73.7 6 of 379 Claude Fable 5 (max reasoning) 10 Jun 2026
UGI: writing scorescore out of 100, higher is better 72.6 8 of 379 Claude Fable 5 (medium reasoning) 10 Jun 2026
UGI: writing scorescore out of 100, higher is better 71.7 15 of 379 Claude Fable 5 (xhigh reasoning) 10 Jun 2026

Not shown: Not other format limits such as character counts or bullet counts.

Vending-Bench 2 · reported by Vending-Bench 2 · 5 results
MeasureValueRankConfigurationDated
Vending-Bench 2: money after a yearUS dollars, higher is better $4,530 32 of 63 Claude Fable 5 1 Oct 2026
Vending-Bench 2: money after a yearUS dollars, higher is better $5,680 19 of 63 Claude Fable 5 (high reasoning) 1 Oct 2026
Vending-Bench 2: money after a yearUS dollars, higher is better $5,019 28 of 63 Claude Fable 5 (low reasoning) 1 Oct 2026
Vending-Bench 2: money after a yearUS dollars, higher is better $4,967 30 of 63 Claude Fable 5 (max reasoning) 1 Oct 2026
Vending-Bench 2: money after a yearUS dollars, higher is better $4,340 34 of 63 Claude Fable 5 (medium reasoning) 1 Oct 2026

Not shown: Not a real business; one simulated market with set rules.

Test your own prompt.

Benchmarks aren't your task. Run your prompt on the models you could use, with every answer checked and costed.