Claude
Trajectory
Concept trajectory
No baseline to compare against
This is the family's first analyzed generation. Once a second member is benched and analyzed, this section will surface the per-concept delta (resolved / persisting / regressed / new).
Members
| Model | Generation | Pass@N | Avg cost / task | Runs | Last run |
|---|---|---|---|---|---|
| — | 80.9% | $0.03 | 6 | 4mo ago | |
| 4 | 82.6% | $0.04 | 6 | 4mo ago | |
| 4 | 84.8% | $0.04 | 3 | 5mo ago | |
| 4 | 60.3% | $0.007 | 3 | 4mo ago | |
| 4 | 53.0% | $0.01 | 3 | 1mo ago | |
| 4 | 82.1% | $0.04 | 6 | 4mo ago | |
| 5 | 91.8% | $0.11 | 3 | 4mo ago | |
| 5 | 91.7% | $0.18 | 3 | 1mo ago | |
| 5 | 79.9% | $0.09 | 3 | 1mo ago | |
| 5 | — | — | 0 | — | |
| 5 | 97.0% | $0.08 | 3 | 25d ago | |
| 5 | — | — | 0 | — |