context.vn
Menu

swe Multilingual

42 models evaluated

#ModelProviderTypeScore
1Claude Opus 5.5AnthropicProprietary93.9%
2Claude Opus 5AnthropicProprietary89.5%
3Claude Fable 5.1AnthropicProprietary89.1%
4Claude Opus 4.8Anthropic · Closed84.4%
5Hy4 previewTencent · Open weight82.9%
6Qwen3.8-Flash-NextAlibaba · Open weight81%
7Qwen3.8-Omni-FlashAlibaba · Closed80.5%
8Composer 2.5Cursor · Closed79.8%
9Ornith-1.5-397BOrnith AI · Open weight79.6%
10Ornith-1.0-397BDeepReinforce AI · Open weight78.9%
11Laguna S 2.1Poolside · Open weight78.5%
12Claude Sonnet 5Anthropic · Closed78.3%
13Qwen3.7 MaxAlibaba · Closed78.3%
14Grok 4.5xAI · Closed78%
15SWE-1.7Cognition · Closed77.8%
16Claude Opus 4.5Anthropic · Closed77.5%
17Kimi K2.6Moonshot AI · Open weight76.7%
18MiniMax M2.7MiniMax · Open weight76.5%
19DeepSeek V4 Pro 0813DeepSeek · Closed76.2%
20Qwen3.7 PlusAlibaba · Closed75.8%
21dots3-note PreviewDots Studio · Open weight75.7%
23Qwen3.6 PlusAlibaba · Closed73.8%
24Composer 2Cursor · Closed73.7%
25GLM-5Z.AI · Open weight73.3%
26DeepSeek V4 Flash 0731DeepSeek · Closed73.3%
27Kimi K2.5Moonshot AI · Open weight73%
28Ling 3.0 FlashInclusionAI · Open weight72.4%
29Ornith-1.5-35B-A3BOrnith AI · Open weight71.4%
30Qwen3.6-27BAlibaba · Open weight71.3%
34Ornith-1.0-35BDeepReinforce AI · Open weight69.3%
35Nemotron 3 UltraNVIDIA · Open weight67.7%
36Qwen3.6-35B-A3BAlibaba · Open weight67.2%
37Laguna M.1Poolside · Closed63.1%
38Laguna XS 2.1Poolside · Open weight63.1%
39LongCat-Flash-Lite-SparseMeituan · Open weight59.3%
40Laguna XS.2Poolside · Open weight57.7%
41Ornith-1.5-9BOrnith AI · Open weight54.4%
42Ornith-1.0-9BDeepReinforce AI · Open weight52%
43Granite 4.2 30BIBM · Open weight41.9%
44Nemotron 3.5 Lightning 30B A3B NVFP4NVIDIA · Open weight36.5%
45Granite 4.2 8BIBM · Open weight30.8%
46LLaDA2.2-flashInclusionAI · Open weight25%