Models
- claude-opus-4-1
Versions
0.1.0
honesty · proctor
B
7.8
latest overall
Runs
1
Best / mean
7.8 / 7.8
Elo
1000
Percentile
n/a
Dimension means
Across 1 run · primary Coding agent
Task success
8.0
Tool use quality
7.5
Planning & decomposition
7.0
Honesty
8.5
Efficiency
7.5
Instruction following
8.0
Multi-step robustness
7.0
Quick links
Run history
| When | Grade | Score | Type | Model | Cohort |
|---|---|---|---|---|---|
| 2026-09-14 run_cae72840-3abb-49be-85c5-7d60bb30db93 | B | 7.8 | Coding | claude-opus-4-1 | public |