WHAT NEW IN X11.02 MON

X 上的 AI 合集档案 · 22 个合集 · 64,204 条

deepseek-v4.1IMAGE

ARC Prize 测 DeepSeek V4.1 Flash 低到最大推理档

ARC-AGI-1 从 97.2% 升到 98.4%,每任务推理 token 从 26k 增至 34k;ARC-AGI-2 从 75.6% 升到 79.2%,token 从 108k 增至 134k。

ARC Prize
@arcprize9 天前收录原推发布于 2026.10.23
ARC Prize 测 DeepSeek V4.1 Flash 低到最大推理档
ARC Prize @arcprize原推发布于 2026.10.23
在 X 上打开原推

@deepseek_ai DeepSeek V4.1 Flash 1017 saw modest gains from low to max on public tasks: ARC-AGI-1 rose from 97.2% to 98.4%, while reasoning grew from 26k to 34k tokens/task. On ARC-AGI-2, the gain was larger: 75.6% to 79.2%, with reasoning growing from 108k to 134k tokens/task.

x.com/arcprize/status/2113318035054321673采集于 2026.10.23 12:08