As of: 2026-10-20 02:15 CEST.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/p/x-arcprize-2112230540283658499/

# “Beam 1.0 from @reflection_ai on ARC-AGI (Verified): - ARC-AGI-2: 23.5%, $0.61/task…”

ARC Prize (@arcprize), X, 2026-10-19.
Source: https://x.com/arcprize/status/2112230540283658499

## Archived text

> Beam 1.0 from @reflection_ai on ARC-AGI (Verified):
> 
> - ARC-AGI-2: 23.5%, $0.61/task
> - ARC-AGI-1: 74.0%, $0.31/task
> 
> Beam’s best scores came at xhigh reasoning, but high was close on ARC-AGI-2: 20.0% versus 23.5%, at about 43% lower cost.

Archived 2026-10-19 via fxtwitter (unofficial).
Counts: 2,957 views, 35 likes, 1 repost, 5 replies (at fetch time)
Media: https://pbs.twimg.com/media/HVAme5eXIAAMnzM.jpg?name=orig

## Cited in

- 2026-10-15: [ARC Prize verifies Gemini 4 Argon at 97.5% on ARC-AGI-3 with Google's harness (49.8% standard), the second lab above 95%](https://postcutoff.com/e/2026-10-15-arc-agi-3-gemini-4-argon-97-5/)