checkpoint evaluation · published benchmark archive

Every published checkpoint, benchmarked.

Published checkpoints are scored against a frozen suite, math and code, that they never trained on. The charts below report pass@1 (correct on the first try), pass@G (the ceiling across G attempts), the headroom between the two, and the in-zone population — problems solved only sometimes, the pool still worth training on. A score here measures the checkpoint; it does not, by itself, show that training caused the difference.