System record
Nine Claude Opus 4.6 research agents
Organization: Anthropic · base model: Claude Opus 4.6
System and setup
| Model version | not reported |
|---|---|
| Software used to run the model | Independent sandboxes with shared forum, code storage and evaluation API |
| Software version | not reported |
| Tools available to the model | Training helpers, remote PGR evaluator, shared findings and code |
| Release date | Not reported |
Autonomy assessments
No autonomy assessment is published for this system.
Published capability results
| Measure | Version | Reported result | Date |
|---|---|---|---|
| Automated weak-to-strong research study | April 2026 chat-preference study | 0.97 PGR | 2026-04 |
Related research
Nine-agent weak-to-strong method searchreport · 2026-04Primary source status belongs to the linked paper; the tracker assessment is separate.Additional system details
- System ID
- automated-w2s-opus46-team
- Organization
- Anthropic
- Base model
- Claude Opus 4.6
- Release date
- Not reported
- Assessment records
- 0
- Recursive evidence records
- 0