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.
34
| 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 |
|---|---|---|
| 142 | 0.111 | -0.414 |
| 112 | 0.081 | -0.391 |
| 238 | 0.140 | -0.385 |
| 27 | 0.073 | -0.368 |
| 171 | 0.038 | -0.364 |
| 276 | 0.140 | -0.327 |
| 57 | 0.057 | -0.324 |
| 33 | 0.087 | -0.300 |
| 44 | 0.129 | -0.300 |
| 262 | 0.082 | -0.298 |
Histogram of problems by the accuracy on each problem.
Histogram of problems by the minimum win rate to solve each problem.