Unverified50% confidenceEventExact time
In the lily teaching-aid test, 6.2 Sol did not deliver on its first 8-minute run, and a rerun cost an additional 11-plus minutes, consuming about 2.05 million tokens in total (of which 1.88 million were cached input and about 23,000 were output tokens).
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
11/19/2026
First Seen
Valid until: 12/3/2026
Sources
Related Entities
Related Claims
UnverifiedIn the motion graphics task, Neon took 22 minutes 32 seconds and consumed 388,000 tokens, while Sol took 44 minutes 42 seconds and consumed 16 million tokens.75% similarUnverifiedBased on measurements with chunks of about 250 words on an RTX A6000, all-MiniLM-L6-v2 processes 1,074.7 chunks per second, taking about 16 minutes for 1 million chunks; Qwen3-Embedding-8B processes 26.1 chunks per second, taking about 10.6 hours for 1 million chunks.67% similarUnverifiedIn a typography replication test, GPT-6 Sol was the fastest, subjectively completing the task in about four to five minutes; Luna took approximately three times as long as Sol (close to twenty minutes); DeepSeek was the slowest at about half an hour.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1188206API
curl https://kongchang.com/api/v1/knowledge/claims/1188206MCP
get_claim(id=1188206)