Unverified50% confidenceFactExact time
Bilibili UP host Tianji divided the 434 experts into 5 tiers: 10 top-tier, 150 excellent, 122 above average, 150 NPC, and 2 useless.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/6/2026
First Seen
Valid until: 1/4/2027
Sources
Related Entities
Related Claims
UnverifiedHY3 internally contains 192 experts and uses a Top-8 routing mechanism.61% similarUnverifiedMuse-Glimmer在九大维度中赢了五个，其中数据提取领先约4.55分为最大差距项，工具/CLI领先3.5分57% similarUnverifiedThe UP host sent the third-round videos from both models to five friends for a blind test, and all five chose the one generated by Opus 5.5.56% similarUnverifiedIn the UP host's KingBench 3 eight-item test, GPT-6 Sol scored 66/80 (82.5%) and Opus 5.5 scored 75/80 (93.75%), with Opus leading by 11.25 percentage points.56% similarUnverifiedOn the AI Builder model intelligence leaderboard, Claude Opus 5.5 Max topped the rankings with 58 points, Xiaomi MiMo V2.6 Pro ranked 9th with 46 points, and Qwen 3.8 Max ranked 10th with 45 points.54% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/979526API
curl https://kongchang.com/api/v1/knowledge/claims/979526MCP
get_claim(id=979526)