Tag
Tencent Hy4 Preview leads on SWE-bench Pro with 770B total parameters, 49B active, and 1M context length, marking their biggest generational leap as an open weights model competing against frontier AI.
OpenAI audited SWE-Bench Pro, a coding benchmark, and found approximately 30% of tasks are broken due to issues like overly strict tests and underspecified prompts, advising model developers to carefully examine results.