X：ARC Prize (@arcprize)· @arcprize·· 4 天前AI 评分
ARC Prize 测试 GLM 5.3 Flash：正式版在 ARC-AGI-1 & 2 上平均提升 15 个百分点
R to @Zai_org: While GLM 5.3 Flash was available in stealth as Ox Alpha on @OpenRouter, we tested it on ARC-AGI-1 & 2 public tasks. When we later tested the official GLM 5.3 Flash through @Baseten, we saw scores rise by an average of 15 percentage points across both benchmarks.
ARC Prize 对 GLM 5.3 Flash 在 ARC-AGI-1 与 ARC-AGI-2 公开任务上做了测试。该模型曾以 Ox Alpha 之名在 OpenRouter 上隐身提供，后经 Baseten 测试官方版 GLM 5.3 Flash，两项基准分数平均上升 15 个百分点。
来源：X：ARC Prize (@arcprize) · x.lingyaoai.com