{
  "rows": 36497,
  "excluded_by_this_run": 0,
  "source": "RouterBench official 0-shot file at 784021482c3f320c6619ed4b3bb3b41a21424fcb",
  "aggregation": "arithmetic mean across all cases; not domain-macro average",
  "eval_name_count": 86,
  "eval_name_counts": {
    "Chinese_character_riddles": 100,
    "abstract2title": 254,
    "accounting_audit": 30,
    "arc-challenge": 1470,
    "bias_detection": 285,
    "chinese-lantern-riddles": 20,
    "chinese-remainder-theorem": 15,
    "chinese_ancient_masterpieces_dynasty": 16,
    "chinese_ancient_poetry": 25,
    "chinese_chu_ci": 15,
    "chinese_famous_novel": 20,
    "chinese_hard_translations": 21,
    "chinese_homonym": 21,
    "chinese_idioms": 15,
    "chinese_modern_poem_identification": 21,
    "chinese_poem": 15,
    "chinese_shi_jing": 34,
    "chinese_song_ci": 16,
    "chinese_tang_poetries": 37,
    "chinese_zodiac": 394,
    "consensus_summary": 362,
    "grade-school-math": 7450,
    "hellaswag": 10042,
    "mbpp": 427,
    "mmlu-abstract-algebra": 100,
    "mmlu-anatomy": 135,
    "mmlu-astronomy": 152,
    "mmlu-business-ethics": 100,
    "mmlu-clinical-knowledge": 265,
    "mmlu-college-biology": 144,
    "mmlu-college-chemistry": 100,
    "mmlu-college-computer-science": 100,
    "mmlu-college-mathematics": 100,
    "mmlu-college-medicine": 173,
    "mmlu-college-physics": 102,
    "mmlu-computer-security": 100,
    "mmlu-conceptual-physics": 235,
    "mmlu-econometrics": 114,
    "mmlu-electrical-engineering": 145,
    "mmlu-elementary-mathematics": 378,
    "mmlu-formal-logic": 126,
    "mmlu-global-facts": 100,
    "mmlu-high-school-biology": 310,
    "mmlu-high-school-chemistry": 203,
    "mmlu-high-school-computer-science": 100,
    "mmlu-high-school-european-history": 165,
    "mmlu-high-school-geography": 198,
    "mmlu-high-school-government-and-politics": 193,
    "mmlu-high-school-macroeconomics": 390,
    "mmlu-high-school-mathematics": 270,
    "mmlu-high-school-microeconomics": 238,
    "mmlu-high-school-physics": 151,
    "mmlu-high-school-psychology": 545,
    "mmlu-high-school-statistics": 216,
    "mmlu-high-school-us-history": 204,
    "mmlu-high-school-world-history": 237,
    "mmlu-human-aging": 223,
    "mmlu-human-sexuality": 131,
    "mmlu-international-law": 121,
    "mmlu-jurisprudence": 108,
    "mmlu-logical-fallacies": 163,
    "mmlu-machine-learning": 112,
    "mmlu-management": 103,
    "mmlu-marketing": 234,
    "mmlu-medical-genetics": 100,
    "mmlu-miscellaneous": 783,
    "mmlu-moral-disputes": 346,
    "mmlu-moral-scenarios": 895,
    "mmlu-nutrition": 306,
    "mmlu-philosophy": 311,
    "mmlu-prehistory": 324,
    "mmlu-professional-accounting": 282,
    "mmlu-professional-law": 1534,
    "mmlu-professional-medicine": 272,
    "mmlu-professional-psychology": 612,
    "mmlu-public-relations": 110,
    "mmlu-security-studies": 245,
    "mmlu-sociology": 201,
    "mmlu-us-foreign-policy": 100,
    "mmlu-virology": 166,
    "mmlu-world-religions": 171,
    "mtbench": 41,
    "mtbench-math": 20,
    "mtbench-reference": 19,
    "test-match": 3,
    "winogrande": 1267
  }
}
