Skip to content
Longterm Wiki
Index
Scorecard_grade·ailabwatch-2025-09|sid_A4XoubikkQ|planning·Record·Profile

Scorecard: ailabwatch 2025-09-01 scored Google DeepMind on Planning = Weak

Verdictconfirmed95%
1 check · 5/25/2026

1 → confirmed

Our claim

entire record
Snapshot
ailabwatch-2025-09
Entity
Google DeepMind
Dimension Slug
planning
Dimension Label
Planning
Score Numeric
26
Score Letter
Weak
Score Raw
26%

Source evidence

1 src · 1 check
confirmed95%Haiku 4.5 · 5/25/2026

NoteThe source is the AI Lab Watch scorecard itself, dated September 2025 (with a note 'Up to date as of September 15'). The scorecard table clearly shows DeepMind scored 26% on the Planning dimension. The claim states scoreRaw: 26% and scoreNumeric: 26, which matches the source exactly. The scoreLetter 'Weak' is a reasonable characterization of a 26% score (typically in the lower range). The publisher (ailabwatch), publishedAt date (2025-09-01, consistent with 'September 2025'), entity (Google DeepMind/DeepMind), and dimension (Planning) all match the source. The only minor note is that the source refers to 'DeepMind' while the claim says 'Google DeepMind' — these are the same entity (DeepMind is owned by Google/Alphabet), so this is not a contradiction.

Case № ailabwatch-2025-09|sid_A4XoubikkQ|planningFiled 5/25/2026Confidence 95%