Export
ARC-AGI
/wiki/arc-agi
The link always opens the latest version of this page.
Ask an AI about it
Open in ChatGPTA new chat that reads this entry from the site Open in ClaudeThe same, in Claude
Sending this to someone?
MarkdownPlain text for notes apps and AI chats
WordA document to edit and annotate
PDFA4, for printing and sharing
ZIPEverything: the documents, the data, and instructions for AI assistants
Share the link instead of a file, and they will always see the latest version.
Files are a snapshot of today. The live page has anything newer.
growing ·
4 feeds
ARC-AGI
Benchmark measuring AI system performance on abstract reasoning tasks with cost-per-task efficiency metrics
Snapshot
Intelligence coverage
Benchmark measuring AI system performance on abstract reasoning tasks with cost-per-task efficiency metrics.
Drawn from 1 news source; the facts and relationships below show where each detail comes from.
Facts 3
| Attribute | Value | Confidence | Sources | Cited |
|---|---|---|---|---|
| Field | ai | low | 1 | source ↗ |
| Nature | concept | low | 1 | source ↗ |
| Maturity | deployed | low | 1 | source ↗ |
Frequently mentioned together 8
Sources 10
- GPT-6 Astra, looped transformers, and hidden reasoning · Hacker News (YC)
- GPT-6 Astra Can Drive Your Desktop, but It Won’t Drive Us to AGI · HackerNoon
- Recreating Minecraft Is Not a Benchmark · Hacker News (YC)
- OpenAI throws Astra into the top-tier model ring · The Register: Security
- 44% on ARC-AGI-1 in 67 cents · Lobsters
5 of 10 sources shown · Pro unlocks the full list