On SWE-Bench Verified, the model achieved a score of 70.6%. This performance is notably competitive when placed alongside significantly larger models; it outpaces DeepSeek-V3.2, which scores 70.2%, ...
Two malicious VS Code extensions have exfiltrated code snippets, API keys, and proprietary algorithms from 1.5 million ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results