Atlas · C11 · Core cognition
Working memory & focus
Holding and using many details at once and staying on task without distraction.
AI Reliable score
6 / 10
Competent pro level · peak 9 · trend ↑ · grade B
Why this score
Huge context windows and no fatigue (long-context reasoning top 88.7%), but the AGI definition scored GPT-5 only 4/10 on working memory across modalities. Strong on text, weaker when juggling visual/audio streams.
On the human scale
2Beginner. Holds a few items briefly
4Average adult. Average adult: follows a long document or conversation, focused for an hour
6Competent pro. Professional: juggles many details of a complex case ← AI today
8Expert. Expert: holds whole complex systems in mind (air-traffic control)
10Best humans. Best human concentration
Future warning
At its best, AI already reaches 9 on this capability. Peak results are never counted in the index; they show where the water may rise next.
Evidence
Artificial Analysis benchmark snapshot (via modelgrep)B
E14 · 2026-11
- Measures
- Independent re-runs of several benchmarks
- AI result
- Long-Context Reasoning 88.7% (Kimi K3); Tau2-Bench 99.1%; IFBench 82.9%; Terminal-Bench Hard 65.9%.
- Humans
- Not published
- On our scale
- Supporting evidence for working memory, language and short agentic plans.
modelgrep.com ↗
A Definition of AGI (Hendrycks et al., CHC-based)B
E07 · 2025-10
- Measures
- 10 CHC cognitive domains, each worth 10% of an 'AGI score'
- AI result
- GPT-5 total 57%: Knowledge 9, Reading-Writing 10, Maths 10, Reasoning 7, Working memory 4, LT memory storage 0, LT memory retrieval 4, Visual 4, Auditory 6, Speed 3 (out of 10 each).
- Humans
- Well-educated adult (definition of 100%)
- On our scale
- Used as a cross-check on the profile shape, not for absolute levels (single model, dated Oct 2025).
arxiv.org ↗
History
First reading: Atlas v0.1, 5 Nov 2026. Every later change will be listed here with its reason.
Disagree? Send a correction
