Anthropic model product
Claude Fable 5
Claude Fable 5 is Anthropic's generally available large language model deployment with production safeguards, exposed through the Claude API as `claude-fable-5`.
Updated Sep 8, 2026. Default version: Claude Fable 5
LLMBoard Score91.6Claude Fable 5
Coverage40%18 benchmark families
Context window1MTokens
Official input price$10Anthropic API
Claude Fable 5 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Claude Fable 5 Benchmark Results
Benchmark scores for Claude Fable 5.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkBlueprint-Bench 2 | Score38.60% | Rank01 | Participants2 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkFrontierCode 1.1 | Score53.50% | Rank01 | Participants17 | Percentile100.00% | EvidenceB | Evaluated |
| BenchmarkFrontierSWE | Score90.00% | Rank01 | Participants16 | Percentile100.00% | EvidenceB | Evaluated |
| BenchmarkHealthBench Professional | Score66.00% | Rank01 | Participants10 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkLegal Agent Benchmark | Score13.30% | Rank01 | Participants13 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Pro | Score80.00% | Rank01 | Participants55 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Verified | Score95.00% | Rank01 | Participants113 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkLM Arena Document Style Control | Score1,506.74 rating | Rank01 | Participants33 | Percentile100.00% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,507.16 rating | Rank01 | Participants210 | Percentile100.00% | EvidenceA | Evaluated |
| BenchmarkLM Arena Vision | Score1,329.46 rating | Rank01 | Participants107 | Percentile100.00% | EvidenceA | Evaluated |
| BenchmarkLM Arena Vision Style Control | Score1,313.06 rating | Rank01 | Participants107 | Percentile100.00% | EvidenceA | Evaluated |
| BenchmarkExploitBench | Score78.00% | Rank02 | Participants6 | Percentile80.00% | EvidenceC | Evaluated |
| BenchmarkOSWorld-Verified | Score85.00% | Rank02 | Participants24 | Percentile95.65% | EvidenceC | Evaluated |
| BenchmarkLM Arena Search Style Control | Score1,228.92 rating | Rank02 | Participants28 | Percentile96.30% | EvidenceA | Evaluated |
| BenchmarkFinance Agent v2 | Score56.31% | Rank03 | Participants26 | Percentile92.00% | EvidenceB | Evaluated |
| BenchmarkFrontierCode | Score46.30% | Rank03 | Participants4 | Percentile33.33% | EvidenceC | Evaluated |
| BenchmarkLM Arena Agent Leaderboard | Score10.23% | Rank03 | Participants49 | Percentile95.83% | EvidenceA | Evaluated |
| BenchmarkLM Arena Agent Praise Complaint | Score19.36% | Rank03 | Participants49 | Percentile95.83% | EvidenceA | Evaluated |
| BenchmarkLM Arena Agent Steerability | Score11.89% | Rank03 | Participants49 | Percentile95.83% | EvidenceA | Evaluated |
| BenchmarkLM Arena Document | Score1,504.25 rating | Rank03 | Participants33 | Percentile93.75% | EvidenceA | Evaluated |
| BenchmarkBioMysteryBench | Score46.10% | Rank04 | Participants5 | Percentile25.00% | EvidenceC | Evaluated |
| BenchmarkHumanity's Last Exam | Score64.50% | Rank04 | Participants103 | Percentile97.06% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench 4.0 | Score44.50% | Rank04 | Participants13 | Percentile75.00% | EvidenceB | Evaluated |
| BenchmarkLM Arena Agent Bash Recovery Steps | Score11.73% | Rank04 | Participants49 | Percentile93.75% | EvidenceA | Evaluated |
| BenchmarkDeepSWE 1.1 | Score70.00% | Rank05 | Participants31 | Percentile86.67% | EvidenceB | Evaluated |
| BenchmarkGDP.pdf | Score29.80% | Rank05 | Participants7 | Percentile33.33% | EvidenceC | Evaluated |
| BenchmarkLiveBench | Score78.31% | Rank05 | Participants38 | Percentile89.19% | EvidenceB | Evaluated |
| BenchmarkLM Arena Search | Score1,230.22 rating | Rank05 | Participants28 | Percentile85.19% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text | Score1,494.14 rating | Rank05 | Participants210 | Percentile98.09% | EvidenceA | Evaluated |
| BenchmarkLM Arena Webdev | Score1,629.05 rating | Rank06 | Participants97 | Percentile94.79% | EvidenceA | Evaluated |
Claude Fable 5 Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenadocument style control | Categoryoverall | Rank01 | Rating / score1,506.74 | Votes5,792 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryfrench | Rank01 | Rating / score1,524.75 | Votes781 | ObservationsN/A | Result date |
| Arenatext style control | Categorycreative writing | Rank01 | Rating / score1,504.45 | Votes5,480 | ObservationsN/A | Result date |
| Arenatext style control | Categoryexclude ties | Rank01 | Rating / score1,527.49 | Votes20,520 | ObservationsN/A | Result date |
| Arenatext style control | Categoryexpert | Rank01 | Rating / score1,548.21 | Votes2,939 | ObservationsN/A | Result date |
| Arenatext style control | Categoryfrench | Rank01 | Rating / score1,527.03 | Votes1,004 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry entertainment and sports and media | Rank01 | Rating / score1,495.87 | Votes6,864 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry writing and literature and language | Rank01 | Rating / score1,512.56 | Votes7,328 | ObservationsN/A | Result date |
| Arenatext style control | Categoryjapanese | Rank01 | Rating / score1,525.96 | Votes367 | ObservationsN/A | Result date |
| Arenatext style control | Categorykorean | Rank01 | Rating / score1,501.26 | Votes548 | ObservationsN/A | Result date |
| Arenatext style control | Categorymath | Rank01 | Rating / score1,529.28 | Votes1,331 | ObservationsN/A | Result date |
| Arenatext style control | Categorynon english | Rank01 | Rating / score1,497.75 | Votes15,261 | ObservationsN/A | Result date |
| Arenatext style control | Categoryoverall | Rank01 | Rating / score1,507.16 | Votes27,189 | ObservationsN/A | Result date |
| Arenatext style control | Categoryrussian | Rank01 | Rating / score1,520.94 | Votes2,706 | ObservationsN/A | Result date |
| Arenatext style control | Categoryspanish | Rank01 | Rating / score1,517.86 | Votes891 | ObservationsN/A | Result date |
| Arenavision | Categorycreative writing vision | Rank01 | Rating / score1,342.71 | Votes685 | ObservationsN/A | Result date |
| Arenavision | Categorydiagram | Rank01 | Rating / score1,366.37 | Votes2,745 | ObservationsN/A | Result date |
| Arenavision | Categoryenglish | Rank01 | Rating / score1,329.40 | Votes4,211 | ObservationsN/A | Result date |
| Arenavision | Categoryhomework | Rank01 | Rating / score1,354.28 | Votes1,169 | ObservationsN/A | Result date |
| Arenavision | Categoryhumor | Rank01 | Rating / score1,347.01 | Votes347 | ObservationsN/A | Result date |
| Arenavision | Categoryocr | Rank01 | Rating / score1,339.90 | Votes7,174 | ObservationsN/A | Result date |
| Arenavision | Categoryoverall | Rank01 | Rating / score1,329.46 | Votes10,002 | ObservationsN/A | Result date |
| Arenavision style control | Categorydiagram | Rank01 | Rating / score1,362.09 | Votes2,745 | ObservationsN/A | Result date |
| Arenavision style control | Categoryenglish | Rank01 | Rating / score1,309.46 | Votes4,211 | ObservationsN/A | Result date |
| Arenavision style control | Categoryhomework | Rank01 | Rating / score1,344.74 | Votes1,169 | ObservationsN/A | Result date |
| Arenavision style control | Categoryhumor | Rank01 | Rating / score1,331.12 | Votes347 | ObservationsN/A | Result date |
| Arenavision style control | Categoryocr | Rank01 | Rating / score1,328.97 | Votes7,174 | ObservationsN/A | Result date |
| Arenavision style control | Categoryoverall | Rank01 | Rating / score1,313.06 | Votes10,002 | ObservationsN/A | Result date |
| Arenasearch style control | Categoryoverall | Rank02 | Rating / score1,228.92 | Votes41,795 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry writing and literature and language | Rank02 | Rating / score1,505.39 | Votes7,328 | ObservationsN/A | Result date |
Claude Fable 5 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $10 input, $50 output per 1M
- Official provider
- Anthropic
- Lowest third-party
- From $3 input, $18.5 output per 1M via Xpersona
- Tracked offerings
- 36
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderKenari | Provider model IDclaude-fable-5 | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderXpersona | Provider model IDclaude-fable-5 | Regionglobal | Input / 1M$3 | Output / 1M$18.5 | Context1M | Updated |
| ProviderOrcaRouter | Provider model IDanthropic/claude-fable-5 | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
| ProviderNanoGPT | Provider model IDanthropic/claude-fable-5 | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
| ProviderVertex | Provider model IDclaude-fable-5@default | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
| ProviderImpossibl | Provider model IDanthropic/claude-fable-5 | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
| ProviderOpenRouter | Provider model IDanthropic/claude-fable-5 | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
| ProviderVertex (Anthropic) | Provider model IDclaude-fable-5@default | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
| ProviderCrossModel | Provider model IDanthropic/claude-fable-5 | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
| ProviderAnthropic | Provider model IDclaude-fable-5 | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
| ProviderAmazon Bedrock | Provider model IDanthropic.claude-fable-5 | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
| ProviderOpper | Provider model IDanthropic/claude-fable-5 | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
| ProviderLLM Gateway | Provider model IDanthropic/claude-fable-5 | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
| ProviderMerge Gateway | Provider model IDanthropic/claude-fable-5 | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
| ProviderCloudflare AI Gateway | Provider model IDanthropic/claude-fable-5 | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
| ProviderZenMux | Provider model IDanthropic/claude-fable-5 | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
| ProviderFreeModel | Provider model IDclaude-fable-5 | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
| ProviderOfox | Provider model IDanthropic/claude-fable-5 | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
| ProviderNeon | Provider model IDclaude-fable-5 | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
| ProviderAzure Cognitive Services | Provider model IDclaude-fable-5 | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
| ProviderOpenCode Zen | Provider model IDclaude-fable-5 | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
| ProviderRequesty | Provider model IDclaude-fable-5 | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
| ProviderAzure | Provider model IDclaude-fable-5 | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
| ProviderVercel AI Gateway | Provider model IDanthropic/claude-fable-5 | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
| ProviderEden AI | Provider model IDanthropic/claude-fable-5 | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
| ProviderDevPass (LLM Gateway) | Provider model IDclaude-fable-5 | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
| ProviderGitHub Copilot | Provider model IDclaude-fable-5 | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
| ProviderModelis | Provider model IDclaude-fable-5 | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
| ProviderKilo Gateway | Provider model IDanthropic/claude-fable-5 | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
| ProviderAbacus | Provider model IDclaude-fable-5 | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
Claude Fable 5 Runtime Performance
Provider-specific output speed and catalog latency for Claude Fable 5. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderAnthropic | Output Speed43.18 tok/s | Catalog Latency15.69 s | Max Input1M | Max Output128K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Claude Fable 5 Specifications
Technical details for the model's default version.
- Version
- Claude Fable 5
- Released
- Jun 9, 2026
- Knowledge cutoff
- Unknown
- Parameters
- N/A
- Context window
- 1M
- Max output
- 128K
- Inputs
- image, text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
Claude Fable 5 Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionClaude Fable 5 | Released | LLMBoard91.63 | ParametersN/A | Context1M | Max output128K | Open weightsNo | LicenseProprietary |
Models similar to Claude Fable 5
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
AN
Claude Mythos
Anthropic
AN
Claude Opus 5
Anthropic
AN
Claude Opus 4.8
Anthropic
AN
Claude Fable 5.1
Anthropic
AN
Claude Opus 4.7
Anthropic
AN
Claude Sonnet 5
Anthropic
What is Claude Fable 5?
Key information about Claude Fable 5 and its available data.
Claude Fable 5 is a safeguarded public deployment of the same underlying weights as Anthropic's restricted Claude Mythos 5 model. It is priced at $10 per million input tokens and $50 per million output tokens.
Data as of 2026-09-08.
FAQ
Common questions about Claude Fable 5.
When was Claude Fable 5 released?
Claude Fable 5's default version was released on Jun 9, 2026.
How much does Claude Fable 5 cost?
Claude Fable 5's official API price is $10 per million input tokens and $50 per million output tokens via Anthropic. The lowest tracked third-party offer starts at $3 input and $18.5 output via Xpersona.
Who created Claude Fable 5?
Claude Fable 5 was created by Anthropic.
What is the context window for Claude Fable 5?
The default version has a 1M token context window.
Is Claude Fable 5 open weight?
No. The default version is not marked as having publicly available weights.