Emad@EMostaque智谱发布 GLM-5.3，基于 743B 基座模型后训练，编码与智能体能力达顶级。Emad Mostaque 指出，该模型与 DeepSeek flash 的更新显示，仅靠后训练即可将性能提升至前沿水平，无法用 logit 蒸馏等解释。GLM-5.3 现已在 cyberdefense 与 GDPval 等硬基准上登顶。
Something has happened with post-training as shown by DeepSeek flash & GLM-5.3 updates.
Same base, big improvement in perf to frontier levels.
Can't explain this by even logit distillation etc
These are all hard benchmarks & GLM 5.3 is now top on by cyberdefense & GDPval!
来源：Emad · x.com
智谱发布 GLM-5.3，基于 743B 基座模型后训练，编码与智能体能力达顶级。Emad Mostaque 指出，该模型与 DeepSeek flash 的更新显示，仅靠后训练即可将性能提升至前沿水平，无法用 logit 蒸馏等解释。GLM-5.3 现已在 cyberdefense 与 GDPval 等硬基准上登顶。
Something has happened with post-training as shown by DeepSeek flash & GLM-5.3 updates.
Same base, big improvement in perf to frontier levels.
Can't explain this by even logit distillation etc
These are all hard benchmarks & GLM 5.3 is now top on by cyberdefense & GDPval!
来源：Emad· x.com