Zhipu's GLM-6 Leaks: reportedly Outperforms Frontier Models in SWE Benchmarks
hunarbatra · x · 2026-08-21
Leaked information suggests that the model known as Ox Alpha is actually a GLM model by Zhipu AI, likely to be named GLM-6. Early results indicate it is approaching "mythos" class performance, absolutely dominating current frontier models in SWE (Software Engineering) and Cyber benchmarks. A DeepSWE screenshot shared in the thread provides evidence of its strong capabilities in code-related tasks.
More from Models
- Meta open-sources Muse Spark Open: 816B-parameter model that runs locally on two Mac Studios — gabriberton · 2026-10-16
- Grok Voice 3.0 Tops Design Arena Speech Leaderboard, Up 7.4 Points — XFreeze · 2026-10-16
- Robotics LLMs tested on 16 tasks: GPT-6 Astra hits 17.2% success vs Fable's 9.1% — pabbeel · 2026-10-16
- Meta open-sources Muse Spark: top US open model, scores just below DeepSeek — bindureddy · 2026-10-16
- TRL adds day-0 support for fine-tuning Muse Spark Open's 816B MoE with LoRA on 64 H100s — QGallouedec · 2026-10-16
- Meta's Muse Spark Open ships detailed eval docs; researcher pushes machine-readable EEE standard — evijit · 2026-10-16