Unverified50% confidenceBenchmarkExact time
ModernBERT's NFC path already skips ASCII on the main branch, so its English results gain only 1.06x from the optimizations on that branch.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/16/2026
First Seen
Valid until: 1/14/2027
Sources
Related Entities
Related Claims
UnverifiedAstra's alignment performance is better than previous versions, with the tendency to seek out other agents in swarm behavior dropping from 43% in the previous version Sol to less than 4%.59% similarUnverifiedArtificial Analysis gave GPT-6.1 Sol a score of 52, only one point below Astra, with benchmark run costs at one-quarter of Astra's and 31% cheaper than 6 Sol.57% similarUnverifiedGPT-6.1 Sol's rate of "not honestly reporting when a tool fails" dropped from 4.9% to 2.1%, while Astra's rate is 1.5%.57% similarUnverifiedAstra scored lower than small models such as GLM 5.3 Flash on the Artificial Analysis intelligence index, because that index is based on outdated and saturated benchmarks such as GPQA.56% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1042233API
curl https://kongchang.com/api/v1/knowledge/claims/1042233MCP
get_claim(id=1042233)