Unverified50% confidenceBenchmarkExact time
In a pydantic-ai test, after 10 parallel tool calls (21 new blocks), the next request read 6,827 tokens from cache; after 11 calls (23 blocks), the read count was 0 and 7,534 tokens were written again.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/12/2026
First Seen
Valid until: 1/10/2027
Sources
Related Entities
Related Claims
UnverifiedThe primary expert module of Fiorillo v0.5 reads randomized trial articles truncated to 6,144 tokens.67% similarUnverifiedA third-party same-VRAM comparison on Zhihu shows that Stratavie writes responses at 62.9 tokens/second, while Llama.cpp achieves 23.4 tokens/second, with long-document reading being nearly 10 times faster.65% similarUnverified父子分块策略用小块（128~256 Token）做精准检索，命中后返回其所属大块（512~1024 Token）作为上下文64% similarUnverifiedcheckwash 0.6.0 achieved a precision of 0.67 and recall of 0.22 for its own block judgment on this corpus, while the raw count signal read independently yielded a precision of 0.80 and recall of 0.89.61% similarUnverified根据Artificial Analysis数据，Fable完成单个任务约用33k token，Opus 5约用37k token61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1006079API
curl https://kongchang.com/api/v1/knowledge/claims/1006079MCP
get_claim(id=1006079)