{"rank":null,"reference":false,"run_id":"6a7fc960cdd0","task":"clinicalqa@0","model":{"id":"dmis-lab/llama-3-meerkat-8b-v1.0","slug":"dmis-lab/llama-3-meerkat-8b-v1.0","name":"Meerkat 8B","type":"llm","developer":"Korea University DMIS Lab"},"tier":"agent","metric":{"name":"accuracy","value":0.6736842105263158,"ci_low":0.6449521531100478,"ci_high":0.7004784688995215},"n":1045,"parse_rate":0.9062200956937799,"cost_usd":0.0,"eval_date":"2026-10-29","url":"https://medbench.kr/r/6a7fc960cdd0","status":"done","listed":true,"current_spec":true,"metrics":{"accuracy":{"value":0.6736842105263158,"ci_low":0.6449521531100478,"ci_high":0.7004784688995215,"n":1045,"n_unparsed":98},"parse_rate":0.9062200956937799,"error_rate":0.0,"parser":"p0.2","by_category":{"Allergy and Immunology":{"value":0.6111111111111112,"n":36},"Cardiology":{"value":0.7528089887640449,"n":89},"Dermatology":{"value":0.75,"n":12},"Emergency Medicine":{"value":0.59375,"n":32},"Endocrinology":{"value":0.7352941176470589,"n":68},"Endocrinology, metabolic, and nutritional disorders":{"value":1.0,"n":1},"Forensic Medicine":{"value":1.0,"n":1},"Gastroenterology":{"value":0.7321428571428571,"n":112},"General Surgery":{"value":0.7413793103448276,"n":58},"Geriatric Medicine":{"value":1.0,"n":1},"Gynecology":{"value":0.5142857142857142,"n":70},"Hematology and Oncology":{"value":0.7916666666666666,"n":48},"Infectious Diseases":{"value":0.6153846153846154,"n":52},"Musculoskeletal (e.g., costochondritis)":{"value":1.0,"n":1},"Nephrology":{"value":0.5585585585585585,"n":111},"Neurology / Neurosurgery":{"value":0.673469387755102,"n":49},"Obstetrics":{"value":0.4444444444444444,"n":18},"Ophthalmology":{"value":1.0,"n":1},"Orthopedic Surgery":{"value":0.625,"n":24},"Otolaryngology":{"value":0.7857142857142857,"n":14},"Otolaryngology (ENT)":{"value":0.7142857142857143,"n":14},"Pediatrics":{"value":0.7142857142857143,"n":56},"Pharmacology":{"value":1.0,"n":1},"Psychiatry":{"value":0.6666666666666666,"n":45},"Pulmonology (Respiratory Medicine)":{"value":0.7230769230769231,"n":65},"Radiology":{"value":1.0,"n":1},"Rheumatology":{"value":0.673469387755102,"n":49},"Urology":{"value":0.6153846153846154,"n":13},"Vascular Surgery":{"value":1.0,"n":2},"nan":{"value":0.0,"n":1}}},"config":{"max_tokens":4096,"prompt":"clinicalqa-p0","temperature":0},"run_key":"0fa39f42fbf375ae9361dfe4e678e38c8b45759ef040c1c818b153dac909ff9e","harness_version":"p0.1","task_spec_hash":"77e37cd0ca6bded7fba03792ec1922342b3f6a7dc3ce602881ce196e6aa7377c","model_id":"dmis-lab/llama-3-meerkat-8b-v1.0","tokens_in":0,"tokens_out":303718,"dataset":{"slug":"clinicalqa","title":"ClinicalQA: Korean Medical Knowledge QA Benchmark","license":"CC BY 4.0 (upstream Apache-2.0)","license_url":"https://creativecommons.org/licenses/by/4.0/","citation":"SNUH-HARI. ClinicalQA: Korean Medical Knowledge QA Benchmark. Seoul National University Hospital Healthcare AI Research Institute, 2025. doi:10.23421/2026.0800"},"predictions_url":"https://medbench.kr/artifacts/6a7fc960cdd0/predictions.parquet","bibtex":"@misc{medbench_6a7fc960cdd0,\n  title = {Meerkat 8B on Korean clinical knowledge (KMLE-level MCQ) (clinicalqa@0)},\n  author = {{medbench.kr}},\n  year = {2026},\n  howpublished = {\\url{https://medbench.kr/r/6a7fc960cdd0}},\n  note = {Evaluated 2026-10-29, harness p0.1, run key 0fa39f42fbf3}\n}"}