Skip to content
Trending storyDeveloping

DeepSeek V4.1 Flash ARC-AGI scores published

1 report1 sourceupdated 2 hours ago

What happened

AI digest

On October 6, ARC Prize published DeepSeek V4.1 Flash's results on the ARC-AGI (Verified) evaluation: 72.9% on ARC-AGI-2 at $0.13 per task, and 94.5% on ARC-AGI-1 at $0.07 per task. Against V4 Flash's best scores, V4.1 Flash gains 5.5 points on ARC-AGI-1 and 11.5 points on ARC-AGI-2, but costs about 250% more per task. The published results show both benchmark scores rising alongside the higher task cost.

Written by AI from the coverage · updated 1 hour ago

Coverage

Follow the reports to see the story from different sides.

Oct 6
  1. AI HOT · Models
    DeepSeek V4.1 Flash 在 ARC-AGI (Verified) 评测成绩公布

    ARC Prize 公布 DeepSeek V4.1 Flash 在 ARC-AGI (Verified) 的成绩:ARC-AGI-2 得分 72.9%、每任务成本 $0.13,ARC-AGI-1 得分 94.5%、每任务成本 $0.07。相比 V4 Flash 最佳成绩,ARC-AGI-1 高 5.5 分、ARC-AGI-2 高 11.5 分,但每任务成本高约 250%。

Heat over time

Not enough continuous observations to draw a trend yet.