Unverified60% confidenceFactExact time
When a model's generation speed exceeds 15–20 TPS, users no longer perceive noticeable waiting during interaction, because humans read English at approximately 4–5 tokens per second
2
Sources
60%
Confidence
Long-term
Relevance
9/6/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedThe average silent reading speed for adults is approximately 200–400 English words per minute, which translates to roughly 4–9 tokens per second.77% similarUnverifiedtps (tokens per second) is a core metric for measuring model inference speed: below 30 tps you will clearly feel the wait, 60-100 tps can satisfy most dialogue and coding needs, and above 100 tps is quite smooth.74% similarVerifiedResearch shows that the average lag time of top simultaneous interpreters is only 2–3 seconds, while the lag of traditional machine simultaneous interpretation systems often exceeds 5 seconds.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/867058API
curl https://kongchang.com/api/v1/knowledge/claims/867058MCP
get_claim(id=867058)