跳到正文
@rohanpaul_ai· @rohanpaul_ai · X·· 14 天前AI 评分42
AI 导读

GLM-5.3 在 @aimlapi 的 5 场景牛顿摆物理测试中击败了今日新上线的隐身模型 Space Bunny Alpha。Space Bunny Alpha 目前在 OpenRouter/OpenCode 隐身发布,拥有 1M token 上下文窗口、原生多模态输入和强编码性能。龙卷风和水滴场景难度更高,两个模型均表现不佳。

正文

GLM-5.3 beat Space Bunny Alpha (the new stealth model launched today) on Newton’s cradle in a 5-scene physics test done by @aimlapi .

Space Bunny Alpha is currently stealth, launched on OpenRouter/OpenCode, with a 1-mn token context window, native multimodal input, strong coding performance.

The tornado and water drop were even harder. Neither model handled those well.

visual result is constrained by the dynamics. you can't compensate for incorrect collision timing or momentum transfer by adding more detail to the environment.

来源:@rohanpaul_ai · x.com