Claude Opus 5.5
claude-opus
Claude model for long-running agentic coding and knowledge work
ReasoningTool CallingAttachments
Context Window
1M
Max Output
128K
Temperature
No
Open Weights
No
Knowledge Cutoff
2026-06
Released
2026-09-22
Last Updated
2026-09-22
Modalities
Input:TextImagePDF
→Output:Text
Benchmarks
| Benchmark | Score | Metric |
|---|---|---|
| Terminal-Bench | 66.4 | score |
| FrontierCode | 54.4 | score |
| CursorBench | 57.8 | score |
| GDPval-AA | 1846 | Elo |
| AutomationBench | 40 | pass rate |
| Humanity's Last Exam | 67.7 | score |
| Terminal-Bench-Science | 58.7 | score |
| OSWorld | 81.8 | partial score |
| Chartography | 89 | score |
Available Providers (4)
| Provider | Input /1M | Output /1M | Cache Read /1M | Cache Write /1M | Reasoning | Status |
|---|---|---|---|---|---|---|
 LLM Gateway | Rp 71.521 | Rp 357.601 | Rp 3.577 | Rp 89.401 | effort | — |
 Merge Gateway | Rp 71.521 | Rp 357.601 | Rp 3.577 | Rp 89.401 | ✓ | — |
 Eden AI | Rp 71.521 | Rp 357.601 | Rp 3.577 | Rp 89.401 | effort | — |
 CrossModel | Rp 71.521 | Rp 357.601 | Rp 3.577 | Rp 89.401 | effort | — |