Public KG record
Claude Opus 5
Recorded overview
Uses specific system prompt instructions to handle sensitive regulatory informat
An evidence-backed entity from the project knowledge graph; detailed tool metadata is still being added.
Recorded details
- Benchmarks: baseline for fixed HydraFusion policies on three benchmarks
- Benchmarks: AutomationBench得分26.9%
- Benchmarks: Agents’ Last Exam最高得分低于GPT-6 Sol的56.4%
- Benchmarks: 与GPT-6 Sol在OSWorld上得分相近
- Benchmarks: 与GPT-6 Luna在DeepSWE上相当
- Benchmarks: 在 AutomationBench 1.0.6 上得分 26.9%
- Benchmarks: 在 Agents’ Last Exam 上的最佳成绩低于 Sol 的 56.4%
- Benchmarks: 在 OSWorld 2.0 offline 上得分 60.3%
Evidence coverage
The KG currently records 10 known information dimensions and has 9 undocumented dimensions, linked to 30 public source articles. These counts describe record coverage, not model performance or verified fit.
Related public records
- Claude Code — uses
- Nous Portal — integrates
- Anthropic — develops
- Anthropic — releases
- Claude Fable 5.1 — competes with