context.vn
Menu

vals Med Code

94 models evaluated

#ModelProviderTypeScore
1Claude Opus 5AnthropicProprietary63.57%
2Google59.06%Gemini 3.1 Pro Preview
3Claude Fable 5AnthropicProprietary56.07%
4Gemini 3 Flash PreviewGoogle55.92%
5Gemini 3.5 FlashGoogle · Closed55.83%
6Claude Opus 4.7Anthropic · Closed54.86%
7Claude Fable 5.1Anthropic · Closed53.51%
8Gemini 3.7 FlashGoogle · Closed53.39%
9Claude Opus 4.8Anthropic · Closed53.22%
10Gemini 3.6 FlashGoogle · Closed53.15%
11GPT-5.1OpenAI · Closed52.73%
12Gemini 3 Pro PreviewGoogle52.20%
13Muse SparkMeta · Closed51.31%
14Gemini 2.5 ProGoogle · Closed50.59%
15Claude Opus 5.5Anthropic · Closed49.80%
16GPT-5.2OpenAI · Closed49.75%
17GPT-5OpenAI49.63%
18Grok 4.7xAI · Closed49.55%
19Muse Spark 1.2Meta · Closed49.35%
20Claude Opus 4.5 ThinkingAnthropic · Closed49.16%
21Claude Opus 4.6 (Adaptive)Anthropic · Closed49.13%
22GPT-5.5OpenAI · Closed49.10%
23Kimi K3Moonshot AI · Closed48.88%
24GPT-6 AstraOpenAI · Closed48.49%
25Claude Opus 4.6Anthropic · Closed48.24%
26Gemini 3.8 FlashGoogle · Closed48.13%
27Gemini 3.1 Flash Lite PreviewGoogle47.60%
28Claude Sonnet 5Anthropic · Closed47.54%
29o3OpenAI · Closed47.29%
30Claude Opus 4.1 20250805 ThinkingAnthropic47.23%
31MiniMax M3MiniMax · Open weight46.29%
32Claude Opus 4.5Anthropic · Closed45.17%
33Grok 4.6xAI · Closed44.71%
34Claude Sonnet 4.5 ThinkingAnthropic · Closed44.13%
35GPT-5.6 SolOpenAI · Closed43.97%
36Gemini 3.5 Flash-LiteGoogle · Closed43.49%
37GPT-5.6 TerraOpenAI · Closed43.41%
38Grok 4.5xAI · Closed43.29%
39Hy4 previewTencent · Open weight43.25%
40GPT-5 miniOpenAI · Closed43.05%
41GLM-5.3Z.AI · Open weight42.86%
42DeepSeek V4 Pro 0813DeepSeek · Closed42.47%
43GPT-5.6 LunaOpenAI · Closed42.39%
44GLM-5.1Z.AI · Open weight41.60%
45DeepSeek V4 Flash 0731DeepSeek · Closed41.41%
46Claude Opus 4.1Anthropic41.37%
47GPT-5.4OpenAI · Closed41.29%
48InklingThinking Machines Lab · Open weight41.19%
49DeepSeek V4.1 FlashDeepSeek · Open weight41.17%
50GPT-5.4 nanoOpenAI · Closed41.03%
51GLM-5.2Z.AI · Open weight40.77%
52Qwen3.8 MaxAlibaba · Open weight40.67%
53Claude Sonnet 4.5Anthropic · Closed40.57%
54Gemini 2.5 Flash Preview 09 2025Google40.54%
56Gemini 2.5 Flash ThinkingGoogle40.36%
57Gemini 2.5 Flash Preview 09 2025 ThinkingGoogle40.33%
58Kimi K2.6Moonshot AI · Open weight40.14%
59Kimi K2.5 ThinkingMoonshot AI39.32%
60Qwen3.7 MaxAlibaba · Closed38.75%
61Nemotron 3 Ultra 550b A55bnvidia38.62%
62Gemini 2.5 FlashGoogle · Closed38.42%
63Grok 4 0709xAI38.08%
64Grok 4.3xAI · Closed38.07%
65Inkling-SmallThinking Machines Lab · Open weight37.89%
66Grok 4 Fast (Reasoning)xAI · Closed37.38%
67Qwen3.6 PlusAlibaba · Closed36.89%
68Llama4 Maverick Instruct BasicFireworks36.51%
69Claude Sonnet 4 20250514 ThinkingAnthropic34.96%
70MiniMax M2.7MiniMax · Open weight34.44%
71Gemini 2.5 Flash Lite Preview 09 2025 ThinkingGoogle34.19%
72MiniMax M2.1MiniMax34.08%
73Claude Sonnet 4Anthropic33.94%
74O4 MiniOpenAI33.79%
75Mistral Medium 3.5Mistral33.75%
76Qwen3.5 FlashAlibaba · Closed33.00%
77GLM-4.7Z.AI · Open weight32.77%
78Claude Haiku 4.5 ThinkingAnthropic · Closed32.68%
79MiMo-V2.5-ProXiaomi · Closed32.48%
80Ling 3.0 Flash 2607ant32.27%
81Grok 4.20 0309 ReasoningxAI32.16%
82MiMo-V2.5Xiaomi · Closed31.89%
83Qwen3 VL PlusAlibaba31.65%
84Qwen3 MaxAlibaba · Closed31.37%
85Mercury 2.5Inception · Closed31.33%
86GPT-5 nanoOpenAI · Closed30.44%
87Grok 4 Fast Non ReasoningxAI30.04%
88Qwen3.8-27BAlibaba · Open weight28.70%
89Grok 4.1 Fast Non ReasoningxAI28.35%
90Grok 4.1 Fast (Reasoning)xAI · Closed28.08%
91Gemini 2.5 Flash LiteGoogle27.11%
92Gemini 2.5 Flash Lite Preview 09 2025Google27.08%
93Meta Llama Llama 4 Scout 17B 16E InstructTogether AI23.31%
94Laguna M.1Poolside · Closed23.11%
95Laguna XS.2Poolside · Open weight21.25%