Unverified50% confidenceBenchmarkExact time
Official side-by-side evaluation shows that the 1017 version improved on all 11 benchmarks, with an average gain of 5.2 points.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/22/2026
First Seen
Valid until: 1/20/2027
Sources
Related Entities
Related Claims
UnverifiedIn passages that actually contain dataset citations, precision increases to 89.5%.67% similarUnverifiedAmong answers exempt from review, the correct rate rose from 97.5% to 99.8%.66% similarUnverifiedRaising the confidence level from 95% to 99% (z-value 2.576) will expand the margin of error by approximately 31% for the same sample size.65% similarUnverifiedThe author's own testing found that the 1017 version's reasoning tokens at the high setting were reduced by about one third compared with the September version, with an even larger drop at the max setting, while accuracy increased.64% similarUnverifiedIn the official benchmark table, almost every test item went up, presenting a pattern of across-the-board gains.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1086984API
curl https://kongchang.com/api/v1/knowledge/claims/1086984MCP
get_claim(id=1086984)