Atlas · C08 · Core cognition
Language: reading & writing
Understanding and producing written and spoken language in context.
AI Reliable score
8 / 10
Expert level · peak 10 · trend → · grade B
Why this score
GPT-5 already scored the maximum on the reading-writing domain of the AGI definition. Instruction-following on precise constraints is still imperfect (top IFBench 82.9%), which keeps Reliable at expert, not best-human.
On the human scale
2Beginner. Simple sentences
4Average adult. Average adult: everyday reading and writing
6Competent pro. Professional: clear reports, emails, summaries
8Expert. Expert: publishable writing, nuanced translation ← AI today
10Best humans. Great writers and translators
Future warning
At its best, AI already reaches 10 on this capability. Peak results are never counted in the index; they show where the water may rise next.
Evidence
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 ↗
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 ↗
History
First reading: Atlas v0.1, 5 Nov 2026. Every later change will be listed here with its reason.
Disagree? Send a correction
