Skip to main content
idapt
HomeAI ModelsPricing
Sign inStart free
All terms

Learn

What is ARC-AGI-2?

Last reviewed July 16, 2026

ARC-AGI-2 is a benchmark of abstract visual puzzles: from a few example grid transformations, the solver must infer the underlying rule and apply it to a new input. Every task is novel by construction, so memorized knowledge does not help; humans solve most tasks while models score far lower. The second edition hardens the format against brute-force strategies and weighs the compute spent, so efficiency counts alongside accuracy.

Why it resists scale

Most benchmarks reward knowledge and pattern coverage, which grow with training data. ARC tasks are designed so each one requires inferring a new rule from a handful of examples: fluid intelligence rather than recall. That is why ARC scores lag far behind knowledge benchmarks even as models grow, and why progress on it is watched as a distinct signal.

Efficiency-aware scoring

ARC-AGI-2 reports not just accuracy but the cost of achieving it: a solver that brute-forces thousands of attempts per puzzle is distinguished from one that reasons its way there. That makes results harder to game with unlimited test-time compute and keeps the leaderboard anchored to something like practical intelligence per dollar.

In idapt

idapt model pages carry each model's published benchmark scores, and the compare view lines several models up so generalization tests like ARC read next to the knowledge and coding lanes.

Model rankingsCompare models

Frequently asked

Related terms

Humanity's Last ExamEpoch Capabilities IndexMETR time horizon

Multi-Model Chat

GPT, Claude, Gemini, Grok, Llama: pick mid-conversation, cheapest-first.

Agents

Skills, scoped permissions, persistent memory: any model you pick.

See it in practice

The fastest way to understand it is to use it. Start free, no credit card.

Try idapt free
  • Home
  • Pricing
  • AI Models
  • Image models
  • Voice models
  • Video models
  • Rankings
  • New models
  • Model status
  • Multi-Model Chat
  • Voice Mode
  • Voice HUD
  • Web Search
  • Image Generation
  • Video Generation
  • Audio Generation
  • Transcription
  • Drive
  • Secrets
  • Sharing
  • Workspaces
  • Tasks
  • Memory
  • Agents
  • Subagents
  • Automations
  • Skills
  • Code Execution
  • Computers
  • Computer Use
  • Cloud Computers
  • Local AI
  • AI Gateway
  • API & SDK
  • CLI
  • MCP
  • Tunnels
  • All features →
  • Blog
  • Use cases
  • Comparisons
  • Best of
  • Learn
  • Free tools
  • Prompts
  • Templates
  • Changelog
  • Help center
  • FAQ
  • Privacy
  • Compare all models
  • Support
  • Developers
  • Quickstarts
  • API reference
  • API pricing
  • CLI
  • MCP
  • Downloads
  • Desktop
  • Badges and embeds
© idapt[email protected]TermsPrivacy PolicyLegal noticeReport content
X (Twitter)