context.vn
Menu

swe Verified

75 models evaluated

#ModelProviderTypeScore
1Claude Opus 5AnthropicProprietary96%
2Claude Mythos 5AnthropicProprietary95.5%
3Claude Fable 5AnthropicProprietary95%
4Claude Opus 4.8Anthropic · Closed88.6%
5Claude Opus 4.7 (Adaptive)Anthropic · Closed87.6%
6Ornith-1.5-397BOrnith AI · Open weight86%
7Claude Sonnet 5Anthropic · Closed85.2%
8GPT-5.3 CodexOpenAI · Closed85%
9Ornith-1.0-397BDeepReinforce AI · Open weight82.4%
10Claude Opus 4.5Anthropic · Closed80.9%
11Claude Opus 4.6Anthropic · Closed80.8%
12DeepSeek V4 Pro 0813DeepSeek · Closed80.6%
13MiniMax M3MiniMax · Open weight80.5%
14Qwen3.7 MaxAlibaba · Closed80.4%
15Kimi K2.6Moonshot AI · Open weight80.2%
16Inkling-SmallThinking Machines Lab · Open weight80.2%
17GPT-5.2OpenAI · Closed80%
18Claude Sonnet 4.6Anthropic · Closed79.6%
20DeepSeek V4 Flash 0731DeepSeek · Closed79%
21Ornith-1.5-35B-A3BOrnith AI · Open weight79%
22Qwen3.6 PlusAlibaba · Closed78.8%
24dots3-note PreviewDots Studio · Open weight78.4%
25BTL-4Bad Theory Labs · Open weight78.4%
26MiMo-V2-ProXiaomi · Closed78%
27GLM-5Z.AI · Open weight77.8%
28Qwen3.7 PlusAlibaba · Closed77.7%
29Apodex 1.1Apodex · Closed77.7%
30InklingThinking Machines Lab · Open weight77.6%
31Mistral Medium 3.5 128BMistral · Open weight77.6%
32Muse SparkMeta · Closed77.4%
33Qwen3.6-27BAlibaba · Open weight77.2%
34Claude Sonnet 4.5Anthropic · Closed77.2%
35Kimi K2.5Moonshot AI · Open weight76.8%
36Kimi K2.5 (Reasoning)Moonshot AI · Closed76.8%
37Grok 4.20xAI · Closed76.7%
38Qwen3.5 397BAlibaba · Open weight76.2%
39Muse Glimmer 30BMeta · Open weight76%
40Ornith-1.0-35BDeepReinforce AI · Open weight75.6%
41MiMo-V2-OmniXiaomi · Closed74.8%
42Laguna M.1Poolside · Closed74.6%
43Claude 4.1 OpusAnthropic · Closed74.5%
44Hy3 PreviewTencent · Open weight74.4%
45GLM-4.7Z.AI · Open weight73.8%
48MAI-Thinking-1Microsoft · Closed73.5%
49Qwen3.6-35B-A3BAlibaba · Open weight73.4%
50MiMo-V2-FlashXiaomi · Open weight73.4%
51Claude Haiku 4.5Anthropic · Closed73.3%
52Claude 4 SonnetAnthropic · Closed72.7%
53MAI-Code-1.1-FlashMicrosoft · Closed72.6%
54Qwen3.5-27BAlibaba · Open weight72.4%
55Qwen3.5-122B-A10BAlibaba · Open weight72%
56Nemotron 3 UltraNVIDIA · Open weight71.9%
57Laguna XS 2.1Poolside · Open weight70.9%
58Grok Code Fast 1xAI · Closed70.8%
59Ornith-1.5-9BOrnith AI · Open weight70.6%
60Solar Pro 4Upstage · Closed70.6%
61Solar Open 2Upstage · Open weight70.4%
62Laguna XS.2Poolside · Open weight69.9%
63Ornith-1.0-9BDeepReinforce AI · Open weight69.4%
64Qwen3.5-35B-A3BAlibaba · Open weight69.2%
65LongCat-Flash-Lite-SparseMeituan · Open weight68.2%
66K-EXAONE 2.0LG AI Research · Open weight68.2%
67Gemini 2.5 ProGoogle · Closed63.8%
68Ternary Bonsai 2 27BPrism ML · Open weight60.8%
69Granite 4.2 30BIBM · Open weight57%
70GPT-4.1OpenAI · Closed54.6%
71ZAYA1-74B-PreviewZyphra · Open weight53.2%
72Nemotron 3.5 Lightning 30B A3B NVFP4NVIDIA · Open weight52.8%
73o3-miniOpenAI · Closed49.3%
74LLaDA2.2-flashInclusionAI · Open weight49.3%
75Claude 3.5 SonnetAnthropic · Closed49%
76Granite 4.2 8BIBM · Open weight47.7%
77MiniCPM5-2BOpenBMB · Open weight46.4%
78DeepSeek V3DeepSeek · Open weight42%
79GPT-4.1 miniOpenAI · Closed23.6%