@deepseek_ai Here's our earlier thread about DeepSeek V4.1 Flash's scores on ARC-AGI-1 and ARC-AGI-2:
DeepSeek V4.1 Flash scores 94.5% on ARC-AGI-1 and 72.9% on ARC-AGI-2
AISummary
ARC Prize says DeepSeek V4.1 Flash scored 94.5% on ARC-AGI-1 at $0.07 per task and 72.9% on ARC-AGI-2 at $0.13 per task. The results beat V4 Flash's best scores by 5.5 points on ARC-AGI-1 and 11.5 points on ARC-AGI-2, but cost about 250% more per task.
Post on XView on X
ARC PrizeVerified on X
@arcprize
Part of a thread · earlier post
DeepSeek V4.1 Flash from @deepseek_ai on ARC-AGI (Verified): - ARC-AGI-2: 72.9%, $0.13/task - ARC-AGI-1: 94.5%, $0.07/task DeepSeek V4.1 Flash beats V4 Flash's best scores by 5.5 points on ARC-AGI-1 and 11.5 on ARC-AGI-2, but costs about 250% more per task.
Source: ARC Prize · x.comPublished · added here