context.vn
Menu

browse Comp

44 models evaluated

#ModelProviderTypeScore
1Atria Dawn PreviewShanghai Artificial Intelligence LaboratoryOpen weights92.5%
2GPT-5.6 SolOpenAIProprietary92.2%
3GPT-6 AstraOpenAIProprietary91.5%
4Kimi K3Moonshot AI · Closed91.2%
5Claude Opus 5Anthropic · Closed90.8%
6GPT-5.5 ProOpenAI · Closed90.1%
7GPT-5.4 ProOpenAI · Closed89.3%
8Step 5 PreviewStepFun · Closed88.7%
9Claude Mythos 5Anthropic · Closed88%
10GPT-5.6 TerraOpenAI · Closed87.5%
11Ornith-1.5-397BOrnith AI · Open weight86.6%
12Claude Sonnet 5Anthropic · Closed84.7%
13GPT-5.5OpenAI · Closed84.4%
14Claude Opus 4.8Anthropic · Closed84.3%
15Claude Opus 4.6Anthropic · Closed83.7%
16MiniMax M3MiniMax · Open weight83.5%
17DeepSeek V4 Pro 0813DeepSeek · Closed83.4%
18GPT-5.6 LunaOpenAI · Closed83.3%
19dots3-note PreviewDots Studio · Open weight83.3%
20Kimi K2.6Moonshot AI · Open weight83.2%
21GPT-5.4OpenAI · Closed82.7%
23Claude Opus 4.7 (Adaptive)Anthropic · Closed79.3%
24Inkling-SmallThinking Machines Lab · Open weight77.4%
25InklingThinking Machines Lab · Open weight77.1%
26Step 3.7 FlashStepFun · Open weight75.8%
27Agents-A1InternScience · Open weight75.5%
28DeepSeek V4 Flash 0731DeepSeek · Closed73.2%
29Ling 3.0 FlashInclusionAI · Open weight72.2%
30GLM-5.1Z.AI · Open weight68%
31Ornith-1.5-35B-A3BOrnith AI · Open weight67.6%
32Agents-A1-4BInternScience · Open weight66.8%
33GPT-5.2OpenAI · Closed65.8%
34Qwen3.5-122B-A10BAlibaba · Open weight63.8%
35Qwen3.5 397BAlibaba · Open weight62%
36Qwen3.5-27BAlibaba · Open weight61%
37Qwen3.5-35B-A3BAlibaba · Open weight61%
38Kimi K2.5Moonshot AI · Open weight60.6%
39Kimi K2.5 (Reasoning)Moonshot AI · Closed60.6%
40Ornith-1.5-9BOrnith AI · Open weight56.4%
42GLM-4.7Z.AI · Open weight52%
43Solar Pro 4Upstage · Closed49.2%
44LongCat-Flash-Lite-SparseMeituan · Open weight48.6%
45Nemotron 3 UltraNVIDIA · Open weight44.4%
46Nemotron 3.5 Lightning 30B A3B NVFP4NVIDIA · Open weight36.8%