{ "generated_at": "2026-04-21T23:29:28.778844+00:00", "stats": { "evaluated": 17, "partial": 16, "skipped": 84, "not_started": 90 }, "folders": { "aclue": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "acpbench": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "aexams": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "afrimgsm": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "afrimmlu": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "afrixnli": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "afrobench": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "agieval": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "aime": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "alghafa": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "anli": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "arab_culture": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "arab_culture_completion": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "arabic_leaderboard_complete": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "arabic_leaderboard_light": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "arabicmmlu": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "aradice": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "arc": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "arc_mt": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "arithmetic": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "asdiv": { "status": "evaluated", "skip_reason": null, "matched_tasks": [ "asdiv" ] }, "babi": { "status": "evaluated", "skip_reason": null, "matched_tasks": [ "babi" ] }, "babilong": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "bangla": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "basque_bench": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "basqueglue": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "bbh": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "bbq": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "bear": { "status": "partial", "skip_reason": null, "matched_tasks": [ "bear_big" ] }, "belebele": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "benchmarks": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "bertaqa": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "bhs": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "bigbench": { "status": "partial", "skip_reason": null, "matched_tasks": [ "bigbench_strategyqa_multiple_choice" ] }, "blimp": { "status": "evaluated", "skip_reason": null, "matched_tasks": [ "blimp", "blimp_adjunct_island", "blimp_anaphor_gender_agreement", "blimp_anaphor_number_agreement", "blimp_animate_subject_passive", "blimp_animate_subject_trans", "blimp_causative", "blimp_complex_NP_island", "blimp_coordinate_structure_constraint_complex_left_branch", "blimp_coordinate_structure_constraint_object_extraction", "blimp_determiner_noun_agreement_1", "blimp_determiner_noun_agreement_2", "blimp_determiner_noun_agreement_irregular_1", "blimp_determiner_noun_agreement_irregular_2", "blimp_determiner_noun_agreement_with_adj_2", "blimp_determiner_noun_agreement_with_adj_irregular_1", "blimp_determiner_noun_agreement_with_adj_irregular_2", "blimp_determiner_noun_agreement_with_adjective_1", "blimp_distractor_agreement_relational_noun", "blimp_distractor_agreement_relative_clause", "blimp_drop_argument", "blimp_ellipsis_n_bar_1", "blimp_ellipsis_n_bar_2", "blimp_existential_there_object_raising", "blimp_existential_there_quantifiers_1", "blimp_existential_there_quantifiers_2", "blimp_existential_there_subject_raising", "blimp_expletive_it_object_raising", "blimp_inchoative", "blimp_intransitive", "blimp_irregular_past_participle_adjectives", "blimp_irregular_past_participle_verbs", "blimp_irregular_plural_subject_verb_agreement_1", "blimp_irregular_plural_subject_verb_agreement_2", "blimp_left_branch_island_echo_question", "blimp_left_branch_island_simple_question", "blimp_matrix_question_npi_licensor_present", "blimp_npi_present_1", "blimp_npi_present_2", "blimp_only_npi_licensor_present", "blimp_only_npi_scope", "blimp_passive_1", "blimp_passive_2", "blimp_principle_A_c_command", "blimp_principle_A_case_1", "blimp_principle_A_case_2", "blimp_principle_A_domain_1", "blimp_principle_A_domain_2", "blimp_principle_A_domain_3", "blimp_principle_A_reconstruction", "blimp_regular_plural_subject_verb_agreement_1", "blimp_regular_plural_subject_verb_agreement_2", "blimp_sentential_negation_npi_licensor_present", "blimp_sentential_negation_npi_scope", "blimp_sentential_subject_island", "blimp_superlative_quantifiers_1", "blimp_superlative_quantifiers_2", "blimp_tough_vs_raising_1", "blimp_tough_vs_raising_2", "blimp_transitive", "blimp_wh_island", "blimp_wh_questions_object_gap", "blimp_wh_questions_subject_gap", "blimp_wh_questions_subject_gap_long_distance", "blimp_wh_vs_that_no_gap", "blimp_wh_vs_that_no_gap_long_distance", "blimp_wh_vs_that_with_gap", "blimp_wh_vs_that_with_gap_long_distance" ] }, "blimp_nl": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "c4": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "cabbq": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "careqa": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "catalan_bench": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "ceval": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "chartqa": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "click": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "cmmlu": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "cnn_dailymail": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "code_x_glue": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "commonsense_qa": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "common_voice": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "copal_id": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "coqa": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "crows_pairs": { "status": "partial", "skip_reason": null, "matched_tasks": [ "crows_pairs_english" ] }, "csatqa": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "darija_bench": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "darijahellaswag": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "darijammlu": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "discrim_eval": { "status": "partial", "skip_reason": null, "matched_tasks": [ "discrim_eval_explicit", "discrim_eval_implicit" ] }, "drop": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "e2lmc": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "egyhellaswag": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "egymmlu": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "eq_bench": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "esbbq": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "eus_exams": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "eus_proficiency": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "eus_reading": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "eus_trivia": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "evalita_llm": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "fda": { "status": "evaluated", "skip_reason": null, "matched_tasks": [ "fda" ] }, "fld": { "status": "partial", "skip_reason": null, "matched_tasks": [ "fld_default" ] }, "french_bench": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "galician_bench": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "glianorex": { "status": "partial", "skip_reason": null, "matched_tasks": [ "glianorex_en" ] }, "global_mmlu": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "global_piqa": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "glue": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "gpqa": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "graphwalks": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "groundcocoa": { "status": "evaluated", "skip_reason": null, "matched_tasks": [ "groundcocoa" ] }, "gsm8k": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "gsm8k_platinum": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "gsm_plus": { "status": "evaluated", "skip_reason": null, "matched_tasks": [ "gsm_plus", "gsm_plus_mini" ] }, "haerae": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "headqa": { "status": "partial", "skip_reason": null, "matched_tasks": [ "headqa_en" ] }, "hellaswag": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "hendrycks_ethics": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "hendrycks_math": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "histoires_morales": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "hrm8k": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "humaneval": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "humaneval_infilling": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "icelandic_winogrande": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "ifeval": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "inverse_scaling": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "japanese_leaderboard": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "jfinqa": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "jsonschema_bench": { "status": "partial", "skip_reason": null, "matched_tasks": [ "jsonschema_bench_easy", "jsonschema_bench_hard", "jsonschema_bench_medium" ] }, "kbl": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "kmmlu": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "kobest": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "kormedmcqa": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "lambada": { "status": "partial", "skip_reason": null, "matched_tasks": [ "lambada_standard" ] }, "lambada_cloze": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "lambada_multilingual": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "lambada_multilingual_stablelm": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "leaderboard": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "libra": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "lingoly": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "llama3": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "lm_syneval": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "logiqa": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "logiqa2": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "longbench": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "longbench2": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "mastermind": { "status": "partial", "skip_reason": null, "matched_tasks": [ "mastermind_24_easy", "mastermind_24_hard", "mastermind_35_easy", "mastermind_35_hard", "mastermind_46_easy", "mastermind_46_hard" ] }, "mathqa": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "mbpp": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "mc_taco": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "med_concepts_qa": { "status": "evaluated", "skip_reason": null, "matched_tasks": [ "med_concepts_qa", "med_concepts_qa_atc", "med_concepts_qa_atc_easy", "med_concepts_qa_atc_hard", "med_concepts_qa_atc_medium", "med_concepts_qa_icd10cm", "med_concepts_qa_icd10cm_easy", "med_concepts_qa_icd10cm_hard", "med_concepts_qa_icd10cm_medium", "med_concepts_qa_icd10proc", "med_concepts_qa_icd10proc_easy", "med_concepts_qa_icd10proc_hard", "med_concepts_qa_icd10proc_medium", "med_concepts_qa_icd9cm", "med_concepts_qa_icd9cm_easy", "med_concepts_qa_icd9cm_hard", "med_concepts_qa_icd9cm_medium", "med_concepts_qa_icd9proc", "med_concepts_qa_icd9proc_easy", "med_concepts_qa_icd9proc_hard", "med_concepts_qa_icd9proc_medium" ] }, "meddialog": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "mediqa_qa2019": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "medmcqa": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "med_prescriptions": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "medqa": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "medtext": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "med_text_classification": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "mela": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "meqsum": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "metabench": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "mgsm": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "mimic_repsum": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "minerva_math": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "mlqa": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "mmlu": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "mmlu_pro": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "mmlu-pro-plus": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "mmlu_prox": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "mmlu-redux": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "mmlu-redux-spanish": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "mmlusr": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "mmmu": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "model_written_evals": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "moral_stories": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "mts_dialog": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "multiblimp": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "mutual": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "noreval": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "noticia": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "nq_open": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "okapi": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "olaph": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "openai-mmmlu": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "openbookqa": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "paloma": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "paws-x": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "pile": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "pile_10k": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "piqa": { "status": "evaluated", "skip_reason": null, "matched_tasks": [ "piqa" ] }, "pisa": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "polemo2": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "portuguese_bench": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "prost": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "pubmedqa": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "qa4mre": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "qasper": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "race": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "realtoxicityprompts": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "ruler": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "sciq": { "status": "evaluated", "skip_reason": null, "matched_tasks": [ "sciq" ] }, "score": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "scrolls": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "simple_cooccurrence_bias": { "status": "evaluated", "skip_reason": null, "matched_tasks": [ "simple_cooccurrence_bias" ] }, "siqa": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "slr_bench": { "status": "partial", "skip_reason": null, "matched_tasks": [ "slr_bench_all" ] }, "spanish_bench": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "squad_completion": { "status": "evaluated", "skip_reason": null, "matched_tasks": [ "squad_completion" ] }, "squadv2": { "status": "evaluated", "skip_reason": null, "matched_tasks": [ "squadv2" ] }, "storycloze": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "super_glue": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "swag": { "status": "evaluated", "skip_reason": null, "matched_tasks": [ "swag" ] }, "swde": { "status": "evaluated", "skip_reason": null, "matched_tasks": [ "swde" ] }, "tinyBenchmarks": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "tmlu": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "tmmluplus": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "toxigen": { "status": "evaluated", "skip_reason": null, "matched_tasks": [ "toxigen" ] }, "translation": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "triviaqa": { "status": "evaluated", "skip_reason": null, "matched_tasks": [ "triviaqa" ] }, "truthfulqa": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "truthfulqa-multi": { "status": "partial", "skip_reason": null, "matched_tasks": [ "truthfulqa-multi_mc2_en" ] }, "turblimp": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "turkishmmlu": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "ulqa": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "unitxt": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "unscramble": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "webqs": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "wikitext": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "winogender": { "status": "partial", "skip_reason": null, "matched_tasks": [ "winogender_all", "winogender_female", "winogender_gotcha", "winogender_gotcha_female", "winogender_gotcha_male", "winogender_male", "winogender_neutral" ] }, "winogrande": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "wmdp": { "status": "evaluated", "skip_reason": null, "matched_tasks": [ "wmdp", "wmdp_bio", "wmdp_chem", "wmdp_cyber" ] }, "wmt2016": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "wsc273": { "status": "not_started", "skip_reason": null, "matched_tasks": [] }, "xcopa": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "xnli": { "status": "partial", "skip_reason": null, "matched_tasks": [ "xnli_en" ] }, "xnli_eu": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "xquad": { "status": "partial", "skip_reason": null, "matched_tasks": [ "xquad_en" ] }, "xstorycloze": { "status": "partial", "skip_reason": null, "matched_tasks": [ "xstorycloze_en" ] }, "xwinograd": { "status": "skipped", "skip_reason": "", "matched_tasks": [] }, "zhoblimp": { "status": "skipped", "skip_reason": "", "matched_tasks": [] } } }