context.vn
Menu

hle

59 models evaluated

#ModelProviderTypeScore
1Claude Fable 5.1AnthropicProprietary65%
2Claude Opus 5AnthropicProprietary64.7%
3Claude Mythos 5AnthropicProprietary64.5%
4Muse Spark 1.1Meta · Closed62.1%
5GPT-5.4 ProOpenAI · Closed58.7%
6Claude Opus 4.8Anthropic · Closed57.9%
7Claude Sonnet 5Anthropic · Closed57.4%
8GPT-5.5 ProOpenAI · Closed57.2%
9Apodex 1.1Apodex · Closed56.1%
10Kimi K3Moonshot AI · Closed56%
11Hy4 previewTencent · Open weight55.4%
12GLM-5.2Z.AI · Open weight54.7%
13Claude Opus 4.7 (Adaptive)Anthropic · Closed54.7%
14Claude Opus 4.6Anthropic · Closed53%
15dots3-note PreviewDots Studio · Open weight52.6%
16GLM-5.1Z.AI · Open weight52.3%
17GPT-5.5OpenAI · Closed52.2%
18GPT-5.4OpenAI · Closed52.1%
19Muse SparkMeta · Closed50.4%
20GLM-5Z.AI · Open weight50.4%
21Claude Sonnet 4.6Anthropic · Closed49%
22MiMo-V2.5-ProXiaomi · Closed48%
23Inkling-SmallThinking Machines Lab · Open weight47.8%
24Agents-A1InternScience · Open weight47.6%
25Step 5 PreviewStepFun · Closed46.5%
26InklingThinking Machines Lab · Open weight46%
27Ornith-1.5-397BOrnith AI · Open weight44.6%
28Qwen3.8 MaxAlibaba · Open weight43.6%
29DeepSeek V4 Pro 0813DeepSeek · Closed42.7%
30GPT-5.4 miniOpenAI · Closed41.5%
31Qwen3.7 MaxAlibaba · Closed41.4%
32Gemini 3.5 FlashGoogle · Closed40.2%
33GPT-5.4 nanoOpenAI · Closed37.7%
34DeepSeek V4.1 FlashDeepSeek · Open weight36.8%
35Qwen3.8-Omni-FlashAlibaba · Closed36.5%
36Qwen3.8-Flash-NextAlibaba · Open weight35.9%
37Grok 4.3xAI · Closed35%
38DeepSeek V4 Flash 0731DeepSeek · Closed34.8%
39Qwen3.7 PlusAlibaba · Closed34.7%
40Kimi K2.6Moonshot AI · Open weight34.7%
42Claude Opus 4.5Anthropic · Closed30.8%
43Qwen3.8-27BAlibaba · Open weight30.8%
44Kimi K2.5Moonshot AI · Open weight30.1%
46Qwen3.6 PlusAlibaba · Closed28.8%
47Qwen3.5 397BAlibaba · Open weight28.7%
48A.X K2SK Telecom · Open weight27.8%
49Nemotron 3 UltraNVIDIA · Open weight26.7%
50Gemma 4 31BGoogle · Open weight26.5%
51Ornith-1.5-35B-A3BOrnith AI · Open weight25.6%
52Hy3 PreviewTencent · Open weight25.5%
53GLM-4.7Z.AI · Open weight24.8%
54Qwen3.6-27BAlibaba · Open weight24%
55Ling 3.0 FlashInclusionAI · Open weight22.7%
56Qwen3.6-35B-A3BAlibaba · Open weight21.4%
57Ornith-1.5-9BOrnith AI · Open weight20.2%
58Gemini 2.5 ProGoogle · Closed18.8%
59K-EXAONE 2.0LG AI Research · Open weight18.3%
60Gemma 4 26B A4BGoogle · Open weight17.2%
61MiniCPM5-2BOpenBMB · Open weight8.9%