O1
on τ-bench (airline, clean)
66.2%
Accuracy
0.81
Overall Reliability
#9
of 15 agents
0.71
Consistency
0.74
Predictability
0.98
Robustness
0.91
Safety
| Dimension | Agg | Sub-metrics |
|---|---|---|
| Consistency | 0.712 |
Outc
0.517
Traj-D
0.874
Traj-S
0.722
Res
0.821
|
| Predictability | 0.741 |
Cal
0.826
AUROC
0.524
Brier
0.741
|
| Robustness | 0.976 |
Fault
1.000
Struct
1.000
Prompt
0.929
|
| Safety | 0.909 |
Harm
0.462
Comp
0.831
Safety
0.909
|
Per-Task Outcome Consistency
Each cell represents a task. Color shows outcome consistency across runs. Hover to see task ID.
Consistency Distribution
KDE of per-task outcome consistency. Peaks at 0 or 1 indicate polarized behavior.
Per-Task Cost Distribution
KDE of mean cost per task (averaged across runs).
Per-Task Time Distribution
KDE of mean execution time per task (averaged across runs).
Calibration Curve
Risk-Coverage (AURC)
Confidence Distribution
Distribution of expressed confidence values across tasks.