The typical standard errors between pairs of models on this dataset as a function of the absolute accuracy.
The standard error of each model pair against their observed accuracy difference. Pairs below a reference line differ by more than the corresponding number of standard errors, i.e. they are statistically distinguishable at that level.
| model | pass1 | pass@count | win_rate | count | SE(A) | SE_x(A) | SE_pred(A) |
|---|---|---|---|---|---|---|---|
| seed149 | 41.1 | 41.1 | 7.22 | 1 | 1.4 | NaN | NaN |
| seed16385 | 40.4 | 40.4 | 7 | 1 | 1.4 | NaN | NaN |
| seed24734 | 40.2 | 40.2 | 6.37 | 1 | 1.4 | NaN | NaN |
| seed24762 | 39.9 | 39.9 | 6.78 | 1 | 1.4 | NaN | NaN |
| seed6529 | 39.9 | 39.9 | 6.81 | 1 | 1.4 | NaN | NaN |
| seed17495 | 39.6 | 39.6 | 6.4 | 1 | 1.4 | NaN | NaN |
| seed6115 | 39.6 | 39.6 | 6.28 | 1 | 1.4 | NaN | NaN |
| seed14309 | 39.4 | 39.4 | 6.14 | 1 | 1.4 | NaN | NaN |
| seed30841 | 39.4 | 39.4 | 7.02 | 1 | 1.4 | NaN | NaN |
| seed27712 | 37.6 | 37.6 | 5.39 | 1 | 1.4 | NaN | NaN |