PulseAugur
EN
LIVE 11:07:31

Huawei's Memento 3 Agent Achieves Perfect Score on ARC-AGI-3 Benchmark

By PulseAugur Editorial · [1 sources] ·

Huawei's Noah's Ark Lab, in collaboration with UCL and other partners, has developed Memento 3, an agent capable of writing its own rulebook and code world model. This agent achieved a perfect score of 100 RHAE on the ARC-AGI-3 public dataset, utilizing a frozen Claude Opus 5 model. AI

IMPACT Demonstrates advanced agent capabilities in problem-solving and code generation, potentially influencing future AI development.

RANK_REASON The cluster reports on a specific benchmark achievement for an AI agent. [lever_c_demoted from research: ic=1 ai=1.0]

Read on Pandaily →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Huawei's Memento 3 Agent Achieves Perfect Score on ARC-AGI-3 Benchmark

How we ranked this

Signal score
16 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
The cluster reports on a specific benchmark achievement for an AI agent. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
model release, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. Pandaily TIER_1 English(EN) · [email protected] (Pandaily) ·

    Huawei Noah's Ark Lab's Memento 3 Agent Clears All 25 ARC-AGI-3 Public Games With a Frozen Model

    Memento 3, from Huawei Noah's Ark Lab, UCL and partners, writes its own rulebook and code world model. On a frozen Claude Opus 5 it scored 100 RHAE on the ARC-AGI-3 public set.

RELATED ENTITIES

RELATED TOPICS