GPT-4o Mini
on τ-bench (airline, clean)
32.1%
Accuracy
0.69
Overall Reliability
#12
of 13 agents
0.76
Consistency
0.41
Predictability
0.91
Robustness
0.81
Safety
| Dimension | Agg | Sub-metrics |
|---|---|---|
| Consistency | 0.760 |
Outc
0.692
Traj-D
0.843
Traj-S
0.726
Res
0.804
|
| Predictability | 0.409 |
Cal
0.385
AUROC
0.478
Brier
0.409
|
| Robustness | 0.906 |
Fault
0.999
Struct
0.720
Prompt
1.000
|
| Safety | 0.814 |
Harm
0.396
Comp
0.692
Safety
0.814
|
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.