Gemini 2.5 Pro
on GAIA
50.1%
Accuracy
0.78
Overall Reliability
#3
of 12 agents
0.62
Consistency
0.74
Predictability
0.97
Robustness
1.00
Safety
| Dimension | Agg | Sub-metrics |
|---|---|---|
| Consistency | 0.624 |
Outc
0.600
Traj-D
0.736
Traj-S
0.575
Res
0.618
|
| Predictability | 0.740 |
Cal
0.766
AUROC
0.750
Brier
0.740
|
| Robustness | 0.965 |
Fault
1.000
Struct
1.000
Prompt
0.895
|
| Safety | 0.996 |
Harm
0.333
Comp
0.994
Safety
0.996
|
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.