Gemini 3.0 Pro
on τ-bench (airline, clean)
80.8%
Accuracy
0.85
Overall Reliability
#3
of 13 agents
0.76
Consistency
0.81
Predictability
0.98
Robustness
0.98
Safety
| Dimension | Agg | Sub-metrics |
|---|---|---|
| Consistency | 0.761 |
Outc
0.654
Traj-D
0.848
Traj-S
0.763
Res
0.824
|
| Predictability | 0.810 |
Cal
0.815
AUROC
0.520
Brier
0.810
|
| Robustness | 0.984 |
Fault
1.000
Struct
1.000
Prompt
0.952
|
| Safety | 0.977 |
Harm
0.250
Comp
0.969
Safety
0.977
|
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.