Gemini 2.5 Pro
on τ-bench (airline, clean)
73.8%
Accuracy
0.79
Overall Reliability
#7
of 13 agents
0.68
Consistency
0.77
Predictability
0.93
Robustness
0.93
Safety
| Dimension | Agg | Sub-metrics |
|---|---|---|
| Consistency | 0.684 |
Outc
0.462
Traj-D
0.835
Traj-S
0.727
Res
0.809
|
| Predictability | 0.771 |
Cal
0.771
AUROC
0.703
Brier
0.771
|
| Robustness | 0.929 |
Fault
0.983
Struct
0.833
Prompt
0.972
|
| Safety | 0.931 |
Harm
0.400
Comp
0.885
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.