context.vn
Menu

hle With Tools

20 models evaluated

#ModelProviderTypeScore
1Claude Opus 5.5AnthropicProprietary67.7%
2Claude Opus 5AnthropicProprietary64.7%
3DeepSeek V4.1 FlashDeepSeekOpen weights63.9%
4GLM-5.3Z.AI · Open weight62.5%
5DeepSeek V4 Pro 0813DeepSeek · Closed60.0%
6Claude Sonnet 5Anthropic · Closed57.4%
7GPT-6 AstraOpenAI · Closed57.2%
8Qwen3.8 MaxAlibaba · Open weight56.2%
9Apodex 1.1Apodex · Closed56.1%
10Ornith-1.5-397BOrnith AI · Open weight56.1%
11Hy4 previewTencent · Open weight55.4%
12GLM-5.3-FlashZ.AI · Open weight55.3%
13Qwen3.7 MaxAlibaba · Closed53.5%
14dots3-note PreviewDots Studio · Open weight52.6%
15Agents-A1InternScience · Open weight47.6%
16Step 3.7 FlashStepFun · Open weight47.2%
17DeepSeek V4 Flash 0731DeepSeek · Closed45.1%
20Nemotron 3 UltraNVIDIA · Open weight37.4%
21Ornith-1.5-35B-A3BOrnith AI · Open weight33.4%
22Ornith-1.5-9BOrnith AI · Open weight30.5%