context.vn
Menu

vals Med Scribe

96 models evaluated

#ModelProviderTypeScore
1Claude Opus 5.5AnthropicProprietary91.43%
2Claude Fable 5.1AnthropicProprietary91.29%
3Claude Opus 5AnthropicProprietary90.98%
4Muse Spark 1.2Meta · Closed90.06%
5Grok 4.7xAI · Closed89.38%
6GLM-5.3-FlashZ.AI · Open weight88.94%
7Muse Spark 1.1Meta · Closed88.89%
8GLM-5.3Z.AI · Open weight88.81%
9Claude Fable 5Anthropic · Closed88.52%
10GPT-5.1OpenAI · Closed88.09%
11Kimi K3Moonshot AI · Closed87.96%
12GPT-6 AstraOpenAI · Closed87.91%
13MiniMax M3MiniMax · Open weight87.25%
14Grok 4.5xAI · Closed86.88%
15GPT-5.5OpenAI · Closed86.87%
16Claude Opus 4.6Anthropic · Closed86.74%
17Grok 4.6xAI · Closed86.53%
18Claude Opus 4.6 (Adaptive)Anthropic · Closed86.13%
19Muse SparkMeta · Closed85.90%
20Claude Opus 4.8Anthropic · Closed85.75%
21DeepSeek V4.1 FlashDeepSeek · Open weight85.50%
22InklingThinking Machines Lab · Open weight85.41%
23Claude Opus 4.5 ThinkingAnthropic · Closed85.32%
24GPT-5.6 SolOpenAI · Closed85.23%
25Claude Haiku 4.5 ThinkingAnthropic · Closed85.23%
26Qwen3.8 MaxAlibaba · Open weight84.95%
27Claude Sonnet 4.5Anthropic · Closed84.52%
28Gemini 3.8 FlashGoogle · Closed84.50%
29GPT-5.6 LunaOpenAI · Closed84.39%
30GPT-5.2OpenAI · Closed84.39%
31Inkling-SmallThinking Machines Lab · Open weight84.11%
32Claude Sonnet 4.5 ThinkingAnthropic · Closed84.10%
33Gemini 3.7 FlashGoogle · Closed83.94%
34Qwen3.8-27BAlibaba · Open weight83.85%
35MiMo-V2.5-ProXiaomi · Closed83.73%
36GPT-5OpenAI83.65%
37Hy4 previewTencent · Open weight83.60%
38GLM-5.2Z.AI · Open weight83.53%
39Claude Opus 4.5Anthropic · Closed83.25%
40Gemini 2.5 Flash ThinkingGoogle82.98%
41Claude Opus 4.7Anthropic · Closed82.95%
42Gemini 2.5 FlashGoogle · Closed82.87%
43GPT-5.6 TerraOpenAI · Closed82.87%
44Grok 4 Fast (Reasoning)xAI · Closed81.63%
45Ling 3.0 Flash 2607ant80.90%
46MiniMax M2.1MiniMax80.78%
47GPT-5 miniOpenAI · Closed80.58%
48DeepSeek V4 Flash 0731DeepSeek · Closed80.36%
49DeepSeek V4 Pro 0813DeepSeek · Closed80.17%
50MiniMax M2.7MiniMax · Open weight79.87%
51Grok 4 Fast Non ReasoningxAI79.72%
52Gemini 3.6 FlashGoogle · Closed79.66%
53Qwen3.7 MaxAlibaba · Closed79.40%
54Grok 4.1 Fast (Reasoning)xAI · Closed78.73%
55Gemini 2.5 Flash Preview 09 2025 ThinkingGoogle78.50%
56Grok 4 0709xAI78.15%
57Kimi K2.6Moonshot AI · Open weight78.15%
58Gemini 2.5 Flash Preview 09 2025Google77.95%
59GPT-5.4OpenAI · Closed77.55%
60Grok 4.1 Fast Non ReasoningxAI77.46%
61Qwen3 VL PlusAlibaba77.13%
62GPT-5.4 nanoOpenAI · Closed77.09%
63Qwen3.6 PlusAlibaba · Closed76.96%
64o3OpenAI · Closed76.65%
65Gemini 3.5 FlashGoogle · Closed76.57%
66Kimi K2.5 ThinkingMoonshot AI76.44%
67Gemini 3.1 Pro PreviewGoogle76.11%
68Claude Sonnet 5Anthropic · Closed76.05%
69Gemini 2.5 Flash Lite Preview 09 2025Google75.82%
71Grok 4.3xAI · Closed74.40%
72Claude Opus 4.1 20250805 ThinkingAnthropic73.90%
73Gemini 2.5 ProGoogle · Closed73.55%
74GPT-5 nanoOpenAI · Closed72.86%
75Gemini 2.5 Flash LiteGoogle72.83%
76Qwen3 MaxAlibaba · Closed72.71%
77Claude Sonnet 4Anthropic72.41%
78GLM-5.1Z.AI · Open weight72.27%
79MiMo-V2.5Xiaomi · Closed72.15%
80Gemini 3 Pro PreviewGoogle72.04%
81Claude Opus 4.1Anthropic71.75%
82Gemini 3.5 Flash-LiteGoogle · Closed70.89%
83Qwen3.5 FlashAlibaba · Closed70.62%
84Gemini 3 Flash PreviewGoogle69.92%
85Claude Sonnet 4 20250514 ThinkingAnthropic69.35%
86O4 MiniOpenAI69.14%
87GLM-4.7Z.AI · Open weight68.63%
88Mistral Medium 3.5Mistral67.73%
89Gemini 2.5 Flash Lite Preview 09 2025 ThinkingGoogle66.88%
90Laguna M.1Poolside · Closed65.91%
91Gemini 3.1 Flash Lite PreviewGoogle63.90%
92Grok 4.20 0309 ReasoningxAI63.41%
93Laguna XS.2Poolside · Open weight61.43%
94Mercury 2.5Inception · Closed55.09%
95Llama4 Maverick Instruct BasicFireworks54.22%
96Meta Llama Llama 4 Scout 17B 16E InstructTogether AI50.59%
97Nemotron Lightning 3p5 30b A3bFireworks4.27%