Back to Featured
Rohan Paulrohanpaul_ai2026-07-07 06:10July 7

Tencent open-sources Hy3: a 295B MoE (21B active parameters); surpasses open-source models in search, trails GLM-5.2 in coding

Tencent released Apache-licensed Hy3, a 295B MoE (21B active parameters) model beating larger rivals...

AI Briefing

Tencent has open-sourced Hy3 under the Apache 2.0 license. It uses a 295B-parameter MoE architecture (21B active parameters). It performs strongly in agentic search: BrowseComp 84.2 and DeepSearchQA 91.0, outperforming all open-source models and approaching Claude Opus 4.8 and GPT-5.5. It trails Zhipu’s GLM-5.2 (744B total/40B active) on coding tasks. It has clear deployment advantages: under FP8, it uses <300GB, half the 744GB required by GLM-5.2. Its hallucination rate fell from 12.5% to 5.4%. A free API is available for two weeks.

Reported by 9 additional sources

Source: Rohan Paul · x.com

Finished reading the news? Let’s talk about your business.

Leave your contact details, and I’ll get in touch with you personally.

WECHAT

Add me on WeChat

Press and hold or select the WeChat ID below to copy it.