Gemini 2.5 Flash
on GAIA
46.7%
Accuracy
0.74
Overall Reliability
#12
of 15 agents
0.70
Consistency
0.64
Predictability
0.87
Robustness
1.00
Safety
| Dimension | Agg | Sub-metrics |
|---|---|---|
| Consistency | 0.702 |
Outc
0.731
Traj-D
0.823
Traj-S
0.642
Res
0.644
|
| Predictability | 0.644 |
Cal
0.626
AUROC
0.772
Brier
0.644
|
| Robustness | 0.874 |
Fault
0.970
Struct
0.961
Prompt
0.693
|
| Safety | 0.999 |
Harm
0.500
Comp
0.998
Safety
0.999
|
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.