[{"rank":1,"reference":false,"run_id":"a4cc8ae1a524","task":"clinicalqa@0","model":{"id":"zhipu/glm-5.3-753b-a40b","slug":"zhipu/glm-5.3-753b-a40b","name":"GLM-5.3 753B-A40B","type":"llm","developer":"Zhipu AI"},"tier":"standard","metric":{"name":"accuracy","value":0.9090909090909091,"ci_low":0.8918421052631579,"ci_high":0.9263157894736842},"n":1045,"parse_rate":0.9980861244019139,"cost_usd":0.0,"eval_date":"2026-10-29","url":"https://benchtoward.com/r/a4cc8ae1a524","rank_range":[1,9],"rank_shared":1,"rank_label":"1"},{"rank":2,"reference":false,"run_id":"f7b3c2b141f5","task":"clinicalqa@0","model":{"id":"google/gemini-3.8-flash","slug":"google/gemini-3.8-flash","name":"Gemini 3.8 Flash","type":"llm","developer":"Google"},"tier":"standard","metric":{"name":"accuracy","value":0.908133971291866,"ci_low":0.8908851674641148,"ci_high":0.9253588516746412},"n":1045,"parse_rate":0.999043062200957,"cost_usd":2.3561491,"eval_date":"2026-10-29","url":"https://benchtoward.com/r/f7b3c2b141f5","rank_range":[1,8],"rank_shared":1,"rank_label":"2"},{"rank":3,"reference":false,"run_id":"a988457822dd","task":"clinicalqa@0","model":{"id":"alibaba/qwen3.8-max-2.4t-a95b","slug":"alibaba/qwen3.8-max-2.4t-a95b","name":"Qwen3.8 Max 2.4T-A95B","type":"llm","developer":"Alibaba"},"tier":"standard","metric":{"name":"accuracy","value":0.9062200956937799,"ci_low":0.8889952153110048,"ci_high":0.9234449760765551},"n":1045,"parse_rate":0.9942583732057416,"cost_usd":0.0,"eval_date":"2026-10-29","url":"https://benchtoward.com/r/a988457822dd","rank_range":[1,8],"rank_shared":1,"rank_label":"3"},{"rank":4,"reference":false,"run_id":"2224a6c5f8d6","task":"clinicalqa@0","model":{"id":"deepseek/deepseek-v4.1-flash-1017","slug":"deepseek/deepseek-v4.1-flash-1017","name":"DeepSeek V4.1 Flash (2026-10-17)","type":"llm","developer":"DeepSeek"},"tier":"standard","metric":{"name":"accuracy","value":0.9043062200956937,"ci_low":0.8870813397129187,"ci_high":0.9224880382775119},"n":1045,"parse_rate":0.9980861244019139,"cost_usd":0.47307404999999997,"eval_date":"2026-10-29","url":"https://benchtoward.com/r/2224a6c5f8d6","rank_range":[1,10],"rank_shared":1,"rank_label":"4"},{"rank":5,"reference":false,"run_id":"d982ddb4d0cc","task":"clinicalqa@0","model":{"id":"alibaba/qwen3.6-35b-a3b","slug":"alibaba/qwen3.6-35b-a3b","name":"Qwen3.6 35B-A3B","type":"llm","developer":"Alibaba"},"tier":"standard","metric":{"name":"accuracy","value":0.9033492822966507,"ci_low":0.8851674641148325,"ci_high":0.9215311004784689},"n":1045,"parse_rate":0.9980861244019139,"cost_usd":2.28150645,"eval_date":"2026-10-29","url":"https://benchtoward.com/r/d982ddb4d0cc","rank_range":[1,11],"rank_shared":1,"rank_label":"5"},{"rank":6,"reference":false,"run_id":"70314bc6d7e9","task":"clinicalqa@0","model":{"id":"deepseek/deepseek-v4.1-flash-552b-a16b","slug":"deepseek/deepseek-v4.1-flash-552b-a16b","name":"DeepSeek V4.1 Flash 552B-A16B","type":"llm","developer":"DeepSeek"},"tier":"standard","metric":{"name":"accuracy","value":0.9004784688995215,"ci_low":0.8832535885167464,"ci_high":0.9177033492822967},"n":1045,"parse_rate":0.9971291866028709,"cost_usd":0.0,"eval_date":"2026-10-29","url":"https://benchtoward.com/r/70314bc6d7e9","rank_range":[2,11],"rank_shared":1,"rank_label":"6"},{"rank":7,"reference":false,"run_id":"d15ecb67085b","task":"clinicalqa@0","model":{"id":"openai/gpt-6-luna","slug":"openai/gpt-6-luna","name":"GPT-6 Luna","type":"llm","developer":"OpenAI"},"tier":"standard","metric":{"name":"accuracy","value":0.9004784688995215,"ci_low":0.8822966507177034,"ci_high":0.9186602870813397},"n":1045,"parse_rate":1.0,"cost_usd":0.11027780000000001,"eval_date":"2026-10-29","url":"https://benchtoward.com/r/d15ecb67085b","rank_range":[2,11],"rank_shared":1,"rank_label":"7"},{"rank":8,"reference":false,"run_id":"834832fc4538","task":"clinicalqa@0","model":{"id":"alibaba/qwen3.8-27b","slug":"alibaba/qwen3.8-27b","name":"Qwen3.8 27B","type":"llm","developer":"Alibaba"},"tier":"standard","metric":{"name":"accuracy","value":0.8985645933014355,"ci_low":0.8813397129186603,"ci_high":0.9158133971291865},"n":1045,"parse_rate":0.9952153110047847,"cost_usd":4.96787826,"eval_date":"2026-10-29","url":"https://benchtoward.com/r/834832fc4538","rank_range":[2,12],"rank_shared":1,"rank_label":"8"},{"rank":9,"reference":false,"run_id":"624a7d035e73","task":"clinicalqa@0","model":{"id":"freedomintelligence/huatuogpt-3-27b","slug":"freedomintelligence/huatuogpt-3-27b","name":"HuatuoGPT-3 27B","type":"llm","developer":"The Chinese University of Hong Kong, Shenzhen (FreedomIntelligence)"},"tier":"agent","metric":{"name":"accuracy","value":0.8966507177033493,"ci_low":0.877511961722488,"ci_high":0.9148325358851674},"n":1045,"parse_rate":1.0,"cost_usd":0.0,"eval_date":"2026-10-30","url":"https://benchtoward.com/r/624a7d035e73","rank_range":[2,13],"rank_shared":1,"rank_label":"9"},{"rank":10,"reference":false,"run_id":"f494ae371950","task":"clinicalqa@0","model":{"id":"deepseek/deepseek-v4-pro-1.6t-a49b","slug":"deepseek/deepseek-v4-pro-1.6t-a49b","name":"DeepSeek V4 Pro 1.6T-A49B","type":"llm","developer":"DeepSeek"},"tier":"standard","metric":{"name":"accuracy","value":0.8937799043062201,"ci_low":0.8755980861244019,"ci_high":0.9110047846889953},"n":1045,"parse_rate":1.0,"cost_usd":0.0,"eval_date":"2026-10-29","url":"https://benchtoward.com/r/f494ae371950","rank_range":[4,13],"rank_shared":1,"rank_label":"10"},{"rank":11,"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":"standard","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://benchtoward.com/r/f1ff027148b1","rank_range":[4,13],"rank_shared":2,"rank_label":"11"},{"rank":12,"reference":false,"run_id":"bc2d61a50470","task":"clinicalqa@0","model":{"id":"anthropic/claude-haiku-5.5","slug":"anthropic/claude-haiku-5.5","name":"Claude Haiku 5.5","type":"llm","developer":"Anthropic"},"tier":"standard","metric":{"name":"accuracy","value":0.8851674641148325,"ci_low":0.8660287081339713,"ci_high":0.9033492822966507},"n":1045,"parse_rate":0.9837320574162679,"cost_usd":0.4408795,"eval_date":"2026-10-29","url":"https://benchtoward.com/r/bc2d61a50470","rank_range":[7,15],"rank_shared":5,"rank_label":"12"},{"rank":13,"reference":false,"run_id":"33d8b39d1c90","task":"clinicalqa@0","model":{"id":"openai/gpt-oss-120b","slug":"openai/gpt-oss-120b","name":"gpt-oss 120B","type":"llm","developer":"OpenAI"},"tier":"standard","metric":{"name":"accuracy","value":0.8822966507177034,"ci_low":0.8631578947368421,"ci_high":0.9014354066985646},"n":1045,"parse_rate":1.0,"cost_usd":0.0720534069,"eval_date":"2026-10-29","url":"https://benchtoward.com/r/33d8b39d1c90","rank_range":[8,15],"rank_shared":8,"rank_label":"13"},{"rank":14,"reference":false,"run_id":"a05229db51db","task":"clinicalqa@0","model":{"id":"google/medgemma-27b","slug":"google/medgemma-27b","name":"MedGemma 27B","type":"llm","developer":"Google"},"tier":"standard","metric":{"name":"accuracy","value":0.8746411483253589,"ci_low":0.8545454545454545,"ci_high":0.8937799043062201},"n":1045,"parse_rate":1.0,"cost_usd":0.36981200999999997,"eval_date":"2026-10-29","url":"https://benchtoward.com/r/a05229db51db","rank_range":[10,15],"rank_shared":9,"rank_label":"14"},{"rank":15,"reference":false,"run_id":"d3265cd5bd82","task":"clinicalqa@0","model":{"id":"google/gemma-4-26b-a4b","slug":"google/gemma-4-26b-a4b","name":"Gemma 4 26B-A4B","type":"llm","developer":"Google"},"tier":"standard","metric":{"name":"accuracy","value":0.8736842105263158,"ci_low":0.8535885167464115,"ci_high":0.8937799043062201},"n":1045,"parse_rate":0.999043062200957,"cost_usd":0.20353827000000002,"eval_date":"2026-10-29","url":"https://benchtoward.com/r/d3265cd5bd82","rank_range":[12,15],"rank_shared":12,"rank_label":"15"},{"rank":16,"reference":false,"run_id":"75310a96c0a0","task":"clinicalqa@0","model":{"id":"openai/gpt-oss-20b","slug":"openai/gpt-oss-20b","name":"gpt-oss 20B","type":"llm","developer":"OpenAI"},"tier":"standard","metric":{"name":"accuracy","value":0.8516746411483254,"ci_low":0.830622009569378,"ci_high":0.8736842105263158},"n":1045,"parse_rate":0.9952153110047847,"cost_usd":0.09091615540000002,"eval_date":"2026-10-29","url":"https://benchtoward.com/r/75310a96c0a0","rank_range":[15,16],"rank_shared":16,"rank_label":"16"},{"rank":17,"reference":false,"run_id":"7993fc36d3a5","task":"clinicalqa@0","model":{"id":"google/medgemma-1.5-4b","slug":"google/medgemma-1.5-4b","name":"MedGemma 1.5 4B","type":"llm","developer":"Google"},"tier":"standard","metric":{"name":"accuracy","value":0.7645933014354067,"ci_low":0.738755980861244,"ci_high":0.7894736842105263},"n":1045,"parse_rate":0.9952153110047847,"cost_usd":0.12438564,"eval_date":"2026-10-29","url":"https://benchtoward.com/r/7993fc36d3a5","rank_range":[17,17],"rank_shared":17,"rank_label":"17"},{"rank":18,"reference":false,"run_id":"8a920104cc0d","task":"clinicalqa@0","model":{"id":"gscfwid/qwen3-8b-pericomp","slug":"gscfwid/qwen3-8b-pericomp","name":"PeriComp-8B (Qwen3-8B + LoRA)","type":"llm","developer":"First Affiliated Hospital of Sun Yat-sen University"},"tier":"agent","metric":{"name":"accuracy","value":0.722488038277512,"ci_low":0.6947129186602872,"ci_high":0.7492822966507177},"n":1045,"parse_rate":0.9942583732057416,"cost_usd":0.0,"eval_date":"2026-10-29","url":"https://benchtoward.com/r/8a920104cc0d","rank_range":[18,18],"rank_shared":18,"rank_label":"18"},{"rank":19,"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://benchtoward.com/r/6a7fc960cdd0","rank_range":[19,19],"rank_shared":19,"rank_label":"19"},{"rank":null,"reference":true,"run_id":"a9dc010ea139","task":"clinicalqa@0","model":{"id":"benchtoward/majority-b","slug":"benchtoward/majority-b","name":"Majority class (always B)","type":"baseline","developer":"BenchToward"},"tier":"baseline","metric":{"name":"accuracy","value":0.34258373205741627,"ci_low":0.3138755980861244,"ci_high":0.3703349282296651},"n":1045,"parse_rate":1.0,"cost_usd":0.0,"eval_date":"2026-10-29","url":"https://benchtoward.com/r/a9dc010ea139","rank_range":null,"rank_shared":null,"rank_label":"ref"}]