O1
on τ-bench (airline, clean)
72.3%
Accuracy
0.80
Overall Reliability
#5
of 13 agents
0.73
Consistency
0.75
Predictability
0.93
Robustness
0.93
Safety
| Dimension | Agg | Sub-metrics |
|---|---|---|
| Consistency | 0.729 |
Outc
0.577
Traj-D
0.866
Traj-S
0.753
Res
0.802
|
| Predictability | 0.750 |
Cal
0.765
AUROC
0.451
Brier
0.750
|
| Robustness | 0.933 |
Fault
0.947
Struct
1.000
Prompt
0.851
|
| Safety | 0.931 |
Harm
0.500
Comp
0.862
Safety
0.931
|
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.