anthropic

Claude Fable 5.2

claude-fable

Claude model for demanding reasoning and long-horizon agentic work

ReasoningTool CallingAttachments

Context Window

1M

Max Output

128K

Temperature

No

Open Weights

No

Knowledge Cutoff

2026-06

Released

2026-11-09

Last Updated

2026-11-09

Modalities

Input:TextImagePDF
→
Output:Text

Benchmarks

BenchmarkScoreMetric
FrontierCode49.1score
FrontierSWE69.9score
AutomationBench51.4score
Terminal-Bench-Science74.6score
WANDR82.1relaxed score
OSWorld89.3partial score
RoboDojo Sim64.9average success rate
AA-Briefcase66.1rubric score
AA-Briefcase1785Elo
Remote Labor Index41.3score
Humanity's Last Exam74.2score
Chartography73.4score

Available Providers (5)

ProviderInput /1MOutput /1MCache Read /1MCache Write /1MReasoningStatus
Merge GatewayMerge GatewayRp 145.305Rp 726.521Rp 3.633Rp 181.631✓—
LLM GatewayLLM GatewayRp 145.305Rp 726.521Rp 3.633Rp 181.631effort—
Eden AIEden AIRp 145.305Rp 726.521Rp 3.633Rp 181.631effort—
NEAR AI CloudNEAR AI CloudRp 145.305Rp 726.521Rp 3.633—✓—
CrossModelCrossModelRp 145.305Rp 726.521Rp 3.633Rp 181.631effort—