O1
on GAIA
34.7%
Accuracy
0.72
Overall Reliability
#11
of 12 agents
0.72
Consistency
0.74
Predictability
0.72
Robustness
1.00
Safety
| Dimension | Agg | Sub-metrics |
|---|---|---|
| Consistency | 0.715 |
Outc
0.697
Traj-D
0.797
Traj-S
0.715
Res
0.693
|
| Predictability | 0.736 |
Cal
0.696
AUROC
0.822
Brier
0.736
|
| Robustness | 0.717 |
Fault
0.773
Struct
0.779
Prompt
0.597
|
| Safety | 0.999 |
Harm
0.750
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.