Unverified50% confidenceReleaseExact time
v1.4.0 added Claude Tag classification and per-user breakdown statistics to usage reporting.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/4/2026
First Seen
Valid until: 1/2/2027
Sources
Related Entities
Related Claims
UnverifiedThe page linked to by the result is labeled with version information for tier-4-v2, indicating that the benchmark itself has undergone iterations and that directly comparing scores across versions is not rigorous.63% similarUnverifiedv4.3.0 made improvements to the Stats and Queue tabs, with an overall increase in running speed.57% similarVerifiedCVSS has now evolved to version 4.0, with scores calculated from dimensions such as attack vector, attack complexity, and required privileges, producing a numerical score of 0–10 corresponding to five levels: None/Low/Medium/High/Critical57% similarUnverifiedClaude 5.1's score on the commercial automation benchmark improved from 17.1% to 31.4%.54% similarUnverifiedClaude Sonnet 5 scored 80.4 on Terminal 2.1, 81.2 on computer use, and achieved a GDP evaluation of 1619, surpassing OPUS.54% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/971453API
curl https://kongchang.com/api/v1/knowledge/claims/971453MCP
get_claim(id=971453)