Anthropic model product
Claude Fable 5.2
2, which is available only through a verification program.
Updated Nov 11, 2026. Default version: Claude Fable 5.2
LLMBoard Score98.5Claude Fable 5.2
Coverage40%27 benchmark families
Context window1MTokens
Official input price$8Anthropic API
Claude Fable 5.2 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Claude Fable 5.2 Benchmark Results
Benchmark scores for Claude Fable 5.2.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkChartography | Score91.60% | Rank01 | Participants8 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkGlobal-MMLU | Score96.00% | Rank01 | Participants9 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkHumanity's Last Exam | Score73.20% | Rank01 | Participants118 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkOfficeQA Pro | Score72.90% | Rank01 | Participants14 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkSWE-bench Multilingual | Score96.60% | Rank01 | Participants52 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Multimodal | Score74.10% | Rank01 | Participants8 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Pro | Score93.00% | Rank01 | Participants65 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkHumanity's Last Exam (with tools) | Score74.20% | Rank01 | Participants7 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkCursorBench 4.0 | Score60.00% | Rank01 | Participants4 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkFrontierSWE V2 | Score69.90% | Rank01 | Participants7 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkMILU | Score94.10% | Rank01 | Participants4 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkOfficeQA | Score83.40% | Rank01 | Participants4 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkChartography (no tools) | Score73.40% | Rank01 | Participants5 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkOSWorld 2.1 (partial) | Score89.30% | Rank01 | Participants8 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkOSWorld 2.1 (strict) | Score54.60% | Rank01 | Participants7 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkPhysicianBench | Score64.40% | Rank01 | Participants3 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkFrontierCode 2.0 | Score49.10% | Rank01 | Participants2 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkARC-AGI-3 | Score79.26% | Rank02 | Participants6 | Percentile80.00% | EvidenceC | Evaluated |
| BenchmarkHealthBench Professional | Score67.70% | Rank02 | Participants22 | Percentile95.24% | EvidenceC | Evaluated |
| BenchmarkProgram Bench | Score85.60% | Rank02 | Participants20 | Percentile94.74% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench-Science 0.1 | Score74.60% | Rank02 | Participants12 | Percentile90.91% | EvidenceC | Evaluated |
| BenchmarkHealthBench Professional (raw) | Score71.10% | Rank02 | Participants3 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkHealthBench (raw) | Score58.80% | Rank02 | Participants2 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench 4.0 | Score67.60% | Rank03 | Participants35 | Percentile94.12% | EvidenceC | Evaluated |
| BenchmarkAA-Briefcase v1.1 | Score1,785.00 points | Rank03 | Participants7 | Percentile66.67% | EvidenceC | Evaluated |
| BenchmarkGDPval-AA 2.1 | Score1,831.00 points | Rank04 | Participants8 | Percentile57.14% | EvidenceC | Evaluated |
| BenchmarkHealthBench | Score59.60% | Rank05 | Participants16 | Percentile73.33% | EvidenceC | Evaluated |
| BenchmarkAutomationBench | Score51.40% | Rank07 | Participants31 | Percentile80.00% | EvidenceC | Evaluated |
| BenchmarkDeepSWE 1.1 | Score74.30% | Rank10 | Participants54 | Percentile83.02% | EvidenceC | Evaluated |
Claude Fable 5.2 Arena Results
Preference and agent-evaluation results for the default version.
No Arena results
The default version does not have a matching Arena result yet.
Claude Fable 5.2 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $8 input, $40 output per 1M
- Official provider
- Anthropic
- Lowest third-party
- From $8 input, $40 output per 1M via Amazon Bedrock
- Tracked offerings
- 16
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderAmazon Bedrock | Provider model IDanthropic.claude-fable-5-2 | Regionglobal | Input / 1M$8 | Output / 1M$40 | Context1M | Updated |
| ProviderCrossModel | Provider model IDanthropic/claude-fable-5-2 | Regionglobal | Input / 1M$8 | Output / 1M$40 | Context1M | Updated |
| ProviderVercel AI Gateway | Provider model IDanthropic/claude-fable-5.2 | Regionglobal | Input / 1M$8 | Output / 1M$40 | Context1M | Updated |
| ProviderAnthropic | Provider model IDclaude-fable-5-2 | Regionglobal | Input / 1M$8 | Output / 1M$40 | Context1M | Updated |
| ProviderAzure Cognitive Services | Provider model IDclaude-fable-5-2 | Regionglobal | Input / 1M$8 | Output / 1M$40 | Context1M | Updated |
| ProviderVenice AI | Provider model IDclaude-fable-5-2 | Regionglobal | Input / 1M$8 | Output / 1M$40 | Context1M | Updated |
| ProviderDevPass (LLM Gateway) | Provider model IDclaude-fable-5-2 | Regionglobal | Input / 1M$8 | Output / 1M$40 | Context1M | Updated |
| ProviderMerge Gateway | Provider model IDanthropic/claude-fable-5-2 | Regionglobal | Input / 1M$8 | Output / 1M$40 | Context1M | Updated |
| ProviderVertex | Provider model IDclaude-fable-5-2@default | Regionglobal | Input / 1M$8 | Output / 1M$40 | Context1M | Updated |
| ProviderEden AI | Provider model IDanthropic/claude-fable-5-2 | Regionglobal | Input / 1M$8 | Output / 1M$40 | Context1M | Updated |
| ProviderAzure | Provider model IDclaude-fable-5-2 | Regionglobal | Input / 1M$8 | Output / 1M$40 | Context1M | Updated |
| ProviderOpenRouter | Provider model IDanthropic/claude-fable-5.2 | Regionglobal | Input / 1M$8 | Output / 1M$40 | Context1M | Updated |
| ProviderVertex (Anthropic) | Provider model IDclaude-fable-5-2@default | Regionglobal | Input / 1M$8 | Output / 1M$40 | Context1M | Updated |
| ProviderOpenCode | Provider model IDclaude-fable-5-2 | Regionglobal | Input / 1M$8 | Output / 1M$40 | Context1M | Updated |
| ProviderLLM Gateway | Provider model IDanthropic/claude-fable-5-2 | Regionglobal | Input / 1M$8 | Output / 1M$40 | Context1M | Updated |
| ProviderNanoGPT | Provider model IDanthropic/claude-fable-5.2 | Regionglobal | Input / 1M$10 | Output / 1M$50 | Context1M | Updated |
Claude Fable 5.2 Runtime Performance
Provider-specific output speed and catalog latency for Claude Fable 5.2. Runtime does not affect the capability score.
No runtime data
No provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Claude Fable 5.2 Specifications
Technical details for the model's default version.
- Version
- Claude Fable 5.2
- Released
- Nov 9, 2026
- Knowledge cutoff
- Jun 1, 2026
- Parameters
- N/A
- Context window
- 1M
- Max output
- 128K
- Inputs
- image, text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
Claude Fable 5.2 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 5.2 | Released | LLMBoard98.49 | ParametersN/A | Context1M | Max output128K | Open weightsNo | LicenseProprietary |
Models similar to Claude Fable 5.2
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
AN
Claude Mythos 5.2
Anthropic
AN
Claude Opus 5.5
Anthropic
AN
Claude Sonnet 5.5
Anthropic
AN
Claude Mythos
Anthropic
AN
Claude Fable 5.1
Anthropic
AN
Claude Opus 5
Anthropic
What is Claude Fable 5.2?
Key information about Claude Fable 5.2 and its available data.
It is a large language model that accepts text and image input, produces text, supports tool use, and has multilingual and vision support with always-on adaptive thinking. Its context window is 1M tokens, with up to 128K output tokens on the synchronous Messages API.
Data as of 2026-11-10.
FAQ
Common questions about Claude Fable 5.2.
When was Claude Fable 5.2 released?
Claude Fable 5.2's default version was released on Nov 9, 2026.
How much does Claude Fable 5.2 cost?
Claude Fable 5.2's official API price is $8 per million input tokens and $40 per million output tokens via Anthropic. The lowest tracked third-party offer starts at $8 input and $40 output via Amazon Bedrock.
Who created Claude Fable 5.2?
Claude Fable 5.2 was created by Anthropic.
What is the context window for Claude Fable 5.2?
The default version has a 1M token context window.
Is Claude Fable 5.2 open weight?
No. The default version is not marked as having publicly available weights.