Expired85% confidenceFactTime unknown
The top three on the leaderboard were all human teams; the best-performing Agent ranked fourth, and the strongest human team outperformed the strongest Agent by only approximately three times.
1
Sources
85%
Confidence
Medium-term (~90 days)
Relevance
6/1/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 8/30/2026(expired)
Sources
Related Claims
UnverifiedManus completed the task the fastest, but its report quality ranked last among the three.59% similarUnverifiedAll three groups of contestants who observed the defense on-site won awards.58% similarUnverifiedIn 15 AI challenges conducted by a Bilibili content creator, Kimi appeared 5 times and won 1st place 3 times.51% similarUnverifiedIn the blogger's self-built GoldieBench evaluation, Agent A1 scored 4.8/10, ranking second, surpassing Gemma 4 but with a notable gap compared to the Qwen series (approximately 7.14 points).50% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/21649API
curl https://kongchang.com/api/v1/knowledge/claims/21649MCP
get_claim(id=21649)