context.vn
Menu

swe Pro

70 models evaluated

#ModelProviderTypeScore
1Claude Opus 5.5AnthropicProprietary89.9%
2Claude Fable 5.1AnthropicProprietary81.2%
3Claude Mythos 5AnthropicProprietary80.3%
4Claude Fable 5Anthropic · Closed80%
5Claude Opus 5Anthropic · Closed79.2%
6Sakana Fugu-UltraSakana AI · Closed73.7%
7Claude Opus 4.8Anthropic · Closed69.2%
8Qwen3.8 MaxAlibaba · Open weight67.7%
9Hy4 previewTencent · Open weight65.7%
10Ornith-1.5-397BOrnith AI · Open weight65.1%
11Grok 4.5xAI · Closed64.7%
12GPT-5.6 SolOpenAI · Closed64.6%
13Claude Opus 4.7 (Adaptive)Anthropic · Closed64.3%
14GPT-5.6 TerraOpenAI · Closed63.4%
15Qwen3.8-Omni-FlashAlibaba · Closed63.3%
16Claude Sonnet 5Anthropic · Closed63.2%
17GPT-5.6 LunaOpenAI · Closed62.7%
18Qwen3.8-Flash-NextAlibaba · Open weight62.5%
19Ornith-1.0-397BDeepReinforce AI · Open weight62.2%
20GLM-5.2Z.AI · Open weight62.1%
21Qwen3.8-27BAlibaba · Open weight61.7%
22Muse Spark 1.1Meta · Closed61.5%
23dots3-note PreviewDots Studio · Open weight61%
24Qwen3.7 MaxAlibaba · Closed60.6%
26Ornith-1.5-35B-A3BOrnith AI · Open weight59.6%
27Laguna S 2.1Poolside · Open weight59.4%
28MiniMax M3MiniMax · Open weight59%
29Sakana FuguSakana AI · Closed59%
30GPT-5.5OpenAI · Closed58.6%
31Kimi K2.6Moonshot AI · Open weight58.6%
32GLM-5.1Z.AI · Open weight58.4%
33GPT-5.4OpenAI · Closed57.7%
34Qwen3.7 PlusAlibaba · Closed57.6%
35Qwen 3.6 Max (preview)Alibaba · Closed57.3%
36MiMo-V2.5-ProXiaomi · Closed57.2%
37Claude Opus 4.5Anthropic · Closed57.1%
38GPT-5.3 CodexOpenAI · Closed56.8%
39Qwen3.6 PlusAlibaba · Closed56.6%
40Ling 3.0 FlashInclusionAI · Open weight56.6%
41Step 3.7 FlashStepFun · Open weight56.3%
42MiniMax M2.7MiniMax · Open weight56.2%
43MiMo-V2.5Xiaomi · Closed56.1%
44Inkling-SmallThinking Machines Lab · Open weight55.9%
45GPT-5.2OpenAI · Closed55.6%
46DeepSeek V4 Pro 0813DeepSeek · Closed55.4%
47Gemini 3.5 FlashGoogle · Closed55.1%
48GLM-5Z.AI · Open weight55.1%
50InklingThinking Machines Lab · Open weight54.3%
51Gemini 3.5 Flash-LiteGoogle · Closed54.2%
52Qwen3.6-27BAlibaba · Open weight53.5%
53Claude Opus 4.6Anthropic · Closed53.4%
54MAI-Thinking-1Microsoft · Closed52.8%
55DeepSeek V4 Flash 0731DeepSeek · Closed52.6%
56Muse SparkMeta · Closed52.4%
59Grok 4.20xAI · Closed51.8%
60Muse Glimmer 30BMeta · Open weight51.2%
61Qwen3.5 397BAlibaba · Open weight50.9%
62Kimi K2.5Moonshot AI · Open weight50.7%
63Ornith-1.0-35BDeepReinforce AI · Open weight50.4%
64Qwen3.6-35B-A3BAlibaba · Open weight49.5%
65Laguna M.1Poolside · Closed49.2%
67Laguna XS 2.1Poolside · Open weight47.6%
68Ornith-1.5-9BOrnith AI · Open weight47.5%
69Laguna XS.2Poolside · Open weight46.3%
70Ornith-1.0-9BDeepReinforce AI · Open weight42.9%
71LongCat-Flash-Lite-SparseMeituan · Open weight40.6%
72Granite 4.2 30BIBM · Open weight33.3%
73LLaDA2.2-flashInclusionAI · Open weight30.1%
74Granite 4.2 8BIBM · Open weight19.1%
75MiniCPM5-2BOpenBMB · Open weight14.4%