[
  {
    "base_model": "Qwen2.5-0.5B-Instruct",
    "benchmark": "kobest_boolq",
    "eval_set_id": "kobest_boolq-test",
    "score": 58.4
  },
  {
    "base_model": "Qwen2.5-0.5B-Instruct",
    "benchmark": "gsm8k",
    "eval_set_id": "gsm8k-test",
    "score": 41.8
  },
  {
    "base_model": "Qwen2.5-1.5B-Instruct",
    "benchmark": "kobest_boolq",
    "eval_set_id": "kobest_boolq-test",
    "score": 71.5
  },
  {
    "base_model": "Qwen2.5-1.5B-Instruct",
    "benchmark": "gsm8k",
    "eval_set_id": "gsm8k-test",
    "score": 64.1
  },
  {
    "base_model": "Llama-3.2-1B-Instruct",
    "benchmark": "kobest_boolq",
    "eval_set_id": "kobest_boolq-test",
    "score": 54.1
  },
  {
    "base_model": "Llama-3.2-1B-Instruct",
    "benchmark": "gsm8k",
    "eval_set_id": "gsm8k-test",
    "score": 38.6
  },
  {
    "base_model": "gemma-2-2b-it",
    "benchmark": "kobest_boolq",
    "eval_set_id": "kobest_boolq-test",
    "score": 66
  },
  {
    "base_model": "gemma-2-2b-it",
    "benchmark": "gsm8k",
    "eval_set_id": "gsm8k-test",
    "score": 51.2
  },
  {
    "base_model": "EXAONE-3.5-2.4B-Instruct",
    "benchmark": "kobest_boolq",
    "eval_set_id": "kobest_boolq-test",
    "score": 74.8
  },
  {
    "base_model": "EXAONE-3.5-2.4B-Instruct",
    "benchmark": "gsm8k",
    "eval_set_id": "gsm8k-test",
    "score": 63.5
  }
]