Atlas · C06 · Perception
Auditory & speech understanding
Understanding speech, tone and sounds, including in noise and with accents.
AI Reliable score
7 / 10
Competent pro level · peak 9 · trend → · grade B
Why this score
Conversational transcription reached human parity on a standard benchmark years ago; GPT-5 scored 6/10 on the auditory domain of the AGI definition. Noisy, multi-speaker and emotional-tone listening is weaker.
On the human scale
2Beginner. Clear single-speaker speech
4Average adult. Average adult: conversation in mild noise, accents, tone
6Competent pro. Professional: transcribes meetings, hears machine faults ← AI today
8Expert. Expert: simultaneous interpreters, sound engineers
10Best humans. Best human listeners
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
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 ↗
Microsoft Research: human parity in conversational speech recognitionA
E08 · 2016-2017
- Measures
- Word error rate on Switchboard conversational speech
- AI result
- Matched professional transcribers on the benchmark.
- Humans
- Professional human transcribers
- On our scale
- Professional level on clean conversational speech; noisy real-world audio lower.
www.microsoft.com ↗
History
First reading: Atlas v0.1, 5 Nov 2026. Every later change will be listed here with its reason.
Disagree? Send a correction
