MLCR-AA: Medical Long Context Reasoning

Wisedocs의 공개 벤치마크로, 길고 파편화된 의료 기록을 모델이 얼마나 잘 추론하는지 측정하며, 보험 및 의료 사례를 검토하는 전문가가 의존하는 다중 문서 종합을 수행합니다.

모델: 96 현재, 181 전체
중앙값: 15.8%
범위: 0.0%–43.9%

점수 분포

가장 낮음: 0.0%
중앙값: 15.8%
최고: 43.9%

리더보드

지원 중단된 모델 포함

순위	모델	점수
51	Claude Haiku 5.5 (Xhigh) Anthropic	15.0%
52	Claude Opus 5.5 (High, Default Fallback) Anthropic	15.0%
53	GPT-6 Luna (Non-reasoning) OpenAI	15.0%
54	Ling 3.1 Flash 1019 InclusionAI	15.0%
55	Gemini 4 Argon (High) Google	13.9%
56	Nemotron 3.5 Super VL NVIDIA	13.3%
57	Gemini 3.8 Flash (Medium) Google	12.8%
58	MiMo-V2.6-Pro Xiaomi	12.8%
59	Claude Haiku 5.5 (Low) Anthropic	12.2%
60	K2 Horizon 375B A23B Institute of Foundation Models	12.2%
61	Kimi K2.7 Code Kimi	12.2%
62	Ling 3.1 Flash InclusionAI	12.2%
63	GLM-5.3-Flash Z AI	11.7%
64	MiMo-V2.6-Flash Xiaomi	11.7%
65	Gemini 3.1 Pro Preview Google	11.1%
66	GLM-5.3 (Low) Z AI	11.1%
67	Gemini 3.5 Flash-Lite Google	10.6%
68	Gemini 3.8 Flash (High) Google	10.6%
69	Ling 3.0 Tiny InclusionAI	10.0%
70	Mistral Medium 3.5 Mistral	10.0%
71	Qwen3.8 27B (Non-reasoning) Alibaba	10.0%
72	Quasar 438B (Max, Based on GLM-5.2) Multiverse Computing	9.4%
73	Qwen3.5 397B A17B (Reasoning) Alibaba	8.9%
74	Qwen3.7 Plus Alibaba	8.9%
75	Inkling Small Thinking Machines	7.8%
76	Muse Spark Open (Xhigh) Meta	7.8%
77	Qwen3.5 122B A10B (Reasoning) Alibaba	7.8%
78	Qwen3.8 27B (Low) Alibaba	7.8%
79	Solar Mini 4 Upstage	6.7%
80	Inkling (Xhigh) Thinking Machines	6.1%
81	Nemotron 3 Ultra 550B A55B (Reasoning) NVIDIA	5.6%
82	Ling-3.0-flash-VL InclusionAI	5.0%
83	Qwen3.6 35B A3B (Reasoning) Alibaba	5.0%
84	MiniMax-M3 MiniMax	4.4%
85	North Mini Code Cohere	4.4%
86	Ling-3.0-flash-Fin InclusionAI	3.9%
87	Qwen3.8 27B (Medium) Alibaba	3.9%
88	Ring-2.6-1T InclusionAI	3.9%
89	Ministral 3 14B Mistral	2.2%
90	Nemotron 3.5 Lightning NVIDIA	2.2%
91	Command A+ Cohere	1.7%
92	gpt-oss-120b (High) OpenAI	1.7%
93	Mistral Small 4 (Reasoning) Mistral	1.7%
94	gpt-oss-20b (High) OpenAI	1.1%
95	Ministral 3 3B Mistral	0.0%
96	Ministral 3 8B Mistral	0.0%