rlvrif-qwen2.5-1.5b/eval-results/mbpp/metrics.json

{
  "mbpp": {
    "pass@1": {
      "num_entries": 378,
      "avg_tokens": 61,
      "gen_seconds": 22,
      "passing_base_tests": 60.317460317460316,
      "passing_plus_tests": 51.58730158730159
    }
  }
}