There are 1 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.
11
| 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 |
|---|---|---|
| 10 | 0.000 | 0.052 |
| 7 | 0.003 | 0.099 |
| 22 | 0.001 | 0.144 |
| 23 | 0.000 | 0.208 |
| 4 | 0.007 | 0.224 |
| 29 | 0.000 | 0.240 |
| 9 | 0.004 | 0.283 |
| 17 | 0.059 | 0.402 |
| 12 | 0.016 | 0.416 |
| 28 | 0.000 | 0.438 |
Histogram of problems by the accuracy on each problem.
Histogram of problems by the minimum win rate to solve each problem.