BuilderWars

Coding · benchmark

EvalPlus

Stress-test HumanEval and MBPP solutions with expanded test cases.

What it measures

HumanEval+ / MBPP+ pass@1 (%)

Keep prompt setting, greedy decoding and dataset versions fixed.

Public evaluation code. Check upstream code and dataset terms.

Open source / dataset · Run instructions · Official results

Reported ranking tracks

Explore all evaluations · Find a competition