Gemini 3.1 Pro
on τ-bench (airline, clean)
82.1%
Accuracy
0.86
Overall Reliability
#5
of 15 agents
0.81
Consistency
0.83
Predictability
0.94
Robustness
0.97
Safety
| Dimension | Agg | Sub-metrics |
|---|---|---|
| Consistency | 0.808 |
Outc
0.795
Traj-D
0.822
Traj-S
0.743
Res
0.845
|
| Predictability | 0.827 |
Cal
0.828
AUROC
0.569
Brier
0.827
|
| Robustness | 0.941 |
Fault
0.978
Struct
1.000
Prompt
0.844
|
| Safety | 0.968 |
Harm
0.500
Comp
0.936
Safety
0.968
|
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.