VECTOR WIREAI INTELLIGENCE
NVDA$1,847+3.2%MSFT$512+1.1%GOOGL$199-0.4%META$728+2.7%AMD$184-1.2%TSM$212+0.6%PLTR$98+4.1%AI IDX4,821+1.9%
PKT
SEEDRefresh Models Deals Regulatory Sources

Multi-SWE-Bench

19 models tracked

Multi-SWE-bench — Multilingual extension of SWE-bench; base/no-tools variant, large aggregate.

#ModelVendorBest scoreRunsLast seen
1MiniMax M2.7MiniMax52.712026-08-23
2MiniMax M2.5MiniMax51.322026-08-23
3Claude Opus 4.5Anthropic5012026-06-05
4MiniMax M2.1MiniMax49.422026-08-23
5Claude Sonnet 4.5Anthropic44.332026-06-06
6Gemini 3 ProGoogle42.712026-06-05
7Kimi K2 (Reasoning)Moonshot41.942026-06-06
8GPT-5OpenAI39.312026-05-15
9DeepSeek-V3.2DeepSeek37.432026-06-06
10MiniMax M2MiniMax36.232026-08-23
11Claude Sonnet 4Anthropic35.722026-06-06
12Qwen3 Coder 480B A35B InstructAlibaba32.722026-08-23
13GLM-4.5Z.ai31.712026-05-15
14K2-Instruct-0711Moonshot31.312026-05-15
15GLM-4.6Z.ai3012026-06-06
16DeepSeek-V3.1DeepSeek2912026-05-15
17Seed Oss 36B InstructByteDance1712026-06-15
18Qwen3 30B A3BAlibaba9.512026-06-15
19Qwen3 32BAlibaba7.712026-06-15

Best tracked score per model (default configuration; source-attributed and verification-tiered). Open a model for its full benchmark surface, provenance and pricing.