Wholestory

← Voices

Tencent

50%credibility0 / 0 / 0

Why this score Chinese technology conglomerate and AI-model publisher (Hunyuan). Authoritative and self-attesting about its own product releases, specs and prices; motivated and non-independent on capability/quality claims about its own models. Baseline 0.5 matches peer model publishers (alibaba_qwen, zhipu_ai, moonshot_ai).

Tracked statements

1
? unverified
Hy4 preview ranks among the top tier of open-source models; in a Tencent-internal blind evaluation of 203 engineering tasks by 163 experts it averaged 2.99 out of 4.00, slightly ahead of GLM-5.3 (2.92) and Kimi K3 (2.94).

Still unverified. Tencent's own private evaluation; Artificial Analysis lists 25 open-weight models and Hy4 is not among them, so the top-tier claim and the narrow wins over GLM-5.3 and Kimi K3 have no neutral index to check against. Its top open models: Kimi K3 (50), GLM-5.3 (49).

state of ai/leading models/open weight frontier·source ↗