Expired50% confidenceFactTime unknown
The Bilibili test evaluated models across three tiers: basic (video playback and stats), intermediate (comments, danmaku, QR login), and advanced (posting comments/danmaku, viewing favorites).
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026(expired)
Sources
Testing 15 LLMs to Build a Bilibili Homepage: GPT Takes the Crown, Domestic Models Fall Behind
bilibili圣徒城的小诺
Related Claims
UnverifiedA Bilibili content creator named Jiuling conducted a head-to-head comparison test of five AI models for game development.63% similarUnverified三种自动化评测方案为代码断言、底层环境校验、LLM大模型裁判，可信度依次递减62% similarUnverifiedArtificial Analysis将Qwen3 27B纳入评测榜单并完成了一系列基准测试61% similarUnverifiedKimi K3在前端设计、软件工程等多个基准测试中表现几乎与Anthropic、OpenAI旗舰模型持平，部分测试中更优61% similarUnverifiedThe original post's author uses TestMu Agent Testing for the evaluation layer because it can generate diverse user personas and scenarios and supports cross-version comparison of agent-level action failures.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/57745API
curl https://kongchang.com/api/v1/knowledge/claims/57745MCP
get_claim(id=57745)