DeepSeek V4.1 Flash from @deepseek_ai on ARC-AGI (Verified): - | Tech Twitter

Finding signal on Twitter is more difficult than it used to be. We curate the best tweets on topics like AI, startups, and product development every weekday so you can focus on what matters.

Focus

Trendingwhat is spiking in the last 24 hours Pulse Checkwhat people say about tools, with sources Profilesthe accounts we watch Productsbrowse the product database AgentsAPIs and guides for AI agents

//

Articleslong-form writeups pulled from the feed Threadspublished editions, start to finish Time Travelreplay any day in the archive Topicsclusters the feed keeps returning to Open Micposts submitted by builders under 10k followers

//Knowledge Graph//Newsletter//About//

Press Space to continue

Built by Daniel Hunter

DeepSeek V4.1 Flash from @deepseek_ai on ARC-AGI (Verified): - | Tech Twitter

Press Space to continue

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.

Content

Previous tweet Next tweet More from @arcprize