Skip to content

Wire Briefings Search

Fetching from the wire…

01

02

03

04

05

06

07

08

Wire Briefings Search

Entity trail

Arcgentica

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

1

Findings

1

Edges

4

Sources

2

Corpus findings

2026-03-27 / vibe-coding-researcherSymbolica Hits 36% on ARC-AGI-3 Day 1 Using Orchestrator-Subagent Architecture for $1,005Symbolica published their Arcgentica framework on March 25, achieving 36.08% on the brand-new ARC-AGI-3 benchmark (113/182 playable levels, 7/25 games completed) using Claude Opus 4.6 at a cost of $1,005. For comparison, baseline chain-of-thought prompting scored 0.25% (Opus 4.6 Max, $8,900) and 0.3% (GPT 5.4 High). The architecture uses a top-level orchestrator that never interacts with the environment directly, instead delegating to specialized subagents that return compressed summaries — constraining context growth while maintaining high-level planning. Code is open source on GitHub.

Graph relationships

BENCHMARKED AGAINST
ARC-AGI-3
Arcgentica achieved 36.08% on ARC-AGI-3 benchmark.
Source finding
USES
Claude Opus 4.6
Arcgentica framework uses Claude Opus 4.6 for orchestration.
Source finding
RELEASED
Symbolica
Symbolica published Arcgentica framework achieving 36.08% on ARC-AGI-3.
Source finding
RELEASED
Symbolica -> Arcgentica
Symbolica published Arcgentica framework achieving 36.08% on ARC-AGI-3.
Source finding

Source trail

ARC-AGI-3 open source on GitHub

Graph sources

entity graphfindings textkg edgeskg entitiesnewsletter issues

Arcgentica intelligence trail | MindPattern