Unverified50% confidenceEventExact time
William Liu compared the tokenization results of multiple GPT models using a set of fixtures, with the experiment covering seven GPT models, including GPT-5.5, three variants of GPT-5.6 (Sol/Terra/Luna), and three variants of GPT-6 (Astra/Sol/Luna).
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/12/2026
First Seen
Valid until: 1/10/2027
Sources
Related Entities
Related Claims
UnverifiedIn the GPT-5.6 Codex evaluation, three different model tier configurations—Sol, Terra, and Luna—were set up.78% similarUnverifiedAccording to Artificial Analysis data, GPT-6-Sol and 5.6-Sol are approximately 100 tok/s, while GPT-6.1-Sol and GPT-6-Astra are approximately 60 tok/s.75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1009725API
curl https://kongchang.com/api/v1/knowledge/claims/1009725MCP
get_claim(id=1009725)