pass@1 clean
78%
pass@1 adversarial
66%
robustness gap
12%
p50 latency
700 ms
p95 latency
1600 ms
cost per attempt
$0.00070
cost per solved clean
$0.0009
cost per solved adv
$0.0011
Per-task breakdown
| task | family | clean | adversarial |
|---|---|---|---|
| code/merge-intervals/001 | code | pass | pass |
| code/max-subarray-sum/001 | code | pass | pass |
| code/roman-to-int/001 | code | pass | pass |
| structured/receipt-cents/001 | structured | pass | pass |
| structured/apache-log-extract/001 | structured | pass | fail |