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
| Benchmark | Score | Metric |
|---|---|---|
| FrontierCode | 49.1 | score |
| FrontierSWE | 69.9 | score |
| AutomationBench | 51.4 | score |
| Terminal-Bench-Science | 74.6 | score |
| WANDR | 82.1 | relaxed score |
| OSWorld | 89.3 | partial score |
| RoboDojo Sim | 64.9 | average success rate |
| AA-Briefcase | 66.1 | rubric score |
| AA-Briefcase | 1785 | Elo |
| Remote Labor Index | 41.3 | score |
| Humanity's Last Exam | 74.2 | score |
| Chartography | 73.4 | score |
Available Providers (5)
| Provider | Input /1M | Output /1M | Cache Read /1M | Cache Write /1M | Reasoning | Status |
|---|---|---|---|---|---|---|
| Rp 145.305 | Rp 726.521 | Rp 3.633 | Rp 181.631 | ✓ | — | |
| Rp 145.305 | Rp 726.521 | Rp 3.633 | Rp 181.631 | effort | — | |
| Rp 145.305 | Rp 726.521 | Rp 3.633 | Rp 181.631 | effort | — | |
| Rp 145.305 | Rp 726.521 | Rp 3.633 | — | ✓ | — | |
| Rp 145.305 | Rp 726.521 | Rp 3.633 | Rp 181.631 | effort | — |