There are 0 examples not solved by any model.
Solving some of these can be a good signal that your model is indeed better than leading models if these are good problems.
| example_link | model | min_pass1_of_model |
|---|
These are 10 problems with the lowest correlation with the overall evaluation (i.e. better models tend to do worse on these. )
| example_link | pass1_of_ex | tau |
|---|---|---|
| 60 | 0.078 | -0.192 |
| 67 | 0.054 | -0.153 |
| 22 | 0.094 | -0.064 |
| 48 | 0.052 | -0.004 |
| 12 | 0.048 | 0.000 |
| 0 | 0.075 | 0.004 |
| 35 | 0.051 | 0.141 |
| 17 | 0.265 | 0.149 |
| 23 | 0.200 | 0.157 |
| 69 | 0.230 | 0.166 |
Histogram of problems by the accuracy on each problem.
Histogram of problems by the minimum win rate to solve each problem.