{"rank":null,"reference":false,"run_id":"f1ff027148b1","task":"clinicalqa@0","model":{"id":"alibaba/qwen3.8-flash-next-180b-a6b","slug":"alibaba/qwen3.8-flash-next-180b-a6b","name":"Qwen3.8 Flash Next 180B-A6B","type":"llm","developer":"Alibaba"},"tier":"baseline","metric":{"name":"accuracy","value":0.8937799043062201,"ci_low":0.876555023923445,"ci_high":0.9129186602870814},"n":1045,"parse_rate":0.9799043062200957,"cost_usd":0.0,"eval_date":"2026-10-29","url":"https://medbench.kr/r/f1ff027148b1","status":"done","listed":true,"current_spec":true,"metrics":{"accuracy":{"value":0.8937799043062201,"ci_low":0.876555023923445,"ci_high":0.9129186602870814,"n":1045,"n_unparsed":21},"parse_rate":0.9799043062200957,"by_category":{"Allergy and Immunology":{"value":0.8888888888888888,"n":36},"Cardiology":{"value":0.9101123595505618,"n":89},"Dermatology":{"value":0.9166666666666666,"n":12},"Emergency Medicine":{"value":1.0,"n":32},"Endocrinology":{"value":0.8970588235294118,"n":68},"Endocrinology, metabolic, and nutritional disorders":{"value":1.0,"n":1},"Forensic Medicine":{"value":1.0,"n":1},"Gastroenterology":{"value":0.9107142857142857,"n":112},"General Surgery":{"value":0.9310344827586207,"n":58},"Geriatric Medicine":{"value":1.0,"n":1},"Gynecology":{"value":0.7571428571428571,"n":70},"Hematology and Oncology":{"value":0.9791666666666666,"n":48},"Infectious Diseases":{"value":0.8269230769230769,"n":52},"Musculoskeletal (e.g., costochondritis)":{"value":1.0,"n":1},"Nephrology":{"value":0.8558558558558559,"n":111},"Neurology / Neurosurgery":{"value":0.9387755102040817,"n":49},"Obstetrics":{"value":0.7222222222222222,"n":18},"Ophthalmology":{"value":1.0,"n":1},"Orthopedic Surgery":{"value":0.9583333333333334,"n":24},"Otolaryngology":{"value":0.9285714285714286,"n":14},"Otolaryngology (ENT)":{"value":0.8571428571428571,"n":14},"Pediatrics":{"value":0.875,"n":56},"Pharmacology":{"value":1.0,"n":1},"Psychiatry":{"value":0.8666666666666667,"n":45},"Pulmonology (Respiratory Medicine)":{"value":0.9538461538461539,"n":65},"Radiology":{"value":1.0,"n":1},"Rheumatology":{"value":0.9387755102040817,"n":49},"Urology":{"value":0.8461538461538461,"n":13},"Vascular Surgery":{"value":1.0,"n":2},"nan":{"value":0.0,"n":1}}},"config":{"max_tokens":16384,"prompt":"clinicalqa-p0","temperature":0},"run_key":"278df64ba411d2c0da7836e53108a9d655bb8e1868139b63b364b7118fc830ec","harness_version":"p0.1","task_spec_hash":"77e37cd0ca6bded7fba03792ec1922342b3f6a7dc3ce602881ce196e6aa7377c","model_id":"alibaba/qwen3.8-flash-next-180b-a6b","tokens_in":419053,"tokens_out":1982490,"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/f1ff027148b1/predictions.parquet","bibtex":"@misc{medbench_f1ff027148b1,\n  title = {Qwen3.8 Flash Next 180B-A6B on Korean clinical knowledge (KMLE-level MCQ) (clinicalqa@0)},\n  author = {{medbench.kr}},\n  year = {2026},\n  howpublished = {\\url{https://medbench.kr/r/f1ff027148b1}},\n  note = {Evaluated 2026-10-29, harness p0.1, run key 278df64ba411}\n}"}