epoch1
{
  "accuracy": 0.29447372169206665,
  "accuracy_by_candidate_count": {
    "4": 0.29447372169206665
  },
  "accuracy_by_subject": {
    "abstract_algebra": 0.32,
    "anatomy": 0.25925925925925924,
    "astronomy": 0.3092105263157895,
    "business_ethics": 0.32,
    "clinical_knowledge": 0.33584905660377357,
    "college_biology": 0.2708333333333333,
    "college_chemistry": 0.29,
    "college_computer_science": 0.32,
    "college_mathematics": 0.29,
    "college_medicine": 0.2658959537572254,
    "college_physics": 0.38235294117647056,
    "computer_security": 0.33,
    "conceptual_physics": 0.23404255319148937,
    "econometrics": 0.21929824561403508,
    "electrical_engineering": 0.33793103448275863,
    "elementary_mathematics": 0.28835978835978837,
    "formal_logic": 0.23015873015873015,
    "global_facts": 0.17,
    "high_school_biology": 0.3,
    "high_school_chemistry": 0.28078817733990147,
    "high_school_computer_science": 0.3,
    "high_school_european_history": 0.3878787878787879,
    "high_school_geography": 0.2878787878787879,
    "high_school_government_and_politics": 0.34196891191709844,
    "high_school_macroeconomics": 0.30256410256410254,
    "high_school_mathematics": 0.25555555555555554,
    "high_school_microeconomics": 0.29411764705882354,
    "high_school_physics": 0.2980132450331126,
    "high_school_psychology": 0.29174311926605506,
    "high_school_statistics": 0.3055555555555556,
    "high_school_us_history": 0.31862745098039214,
    "high_school_world_history": 0.3333333333333333,
    "human_aging": 0.2062780269058296,
    "human_sexuality": 0.3511450381679389,
    "international_law": 0.371900826446281,
    "jurisprudence": 0.4722222222222222,
    "logical_fallacies": 0.25766871165644173,
    "machine_learning": 0.23214285714285715,
    "management": 0.3106796116504854,
    "marketing": 0.3717948717948718,
    "medical_genetics": 0.39,
    "miscellaneous": 0.280970625798212,
    "moral_disputes": 0.35260115606936415,
    "moral_scenarios": 0.22793296089385476,
    "nutrition": 0.31699346405228757,
    "philosophy": 0.3183279742765273,
    "prehistory": 0.2962962962962963,
    "professional_accounting": 0.28368794326241137,
    "professional_law": 0.2900912646675359,
    "professional_medicine": 0.2426470588235294,
    "professional_psychology": 0.2761437908496732,
    "public_relations": 0.2636363636363636,
    "security_studies": 0.24489795918367346,
    "sociology": 0.36318407960199006,
    "us_foreign_policy": 0.36,
    "virology": 0.3433734939759036,
    "world_religions": 0.3742690058479532
  },
  "num_examples": 14042,
  "split": "test"
}
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support