Tencent Hunyuan thanks Artificial Analysis for its Hy4 evaluation; model scores 35 on Intelligence Index v5
Thanks for the evaluation! We’ll keep improving 🙏
AI BriefingTencent Hunyuan shared and thanked Artificial Analysis for its evaluation of its latest model, Hy4. Hy4 scored 35 on the Artificial Analysis Intelligence Index v5, ranking second among models from Chinese labs behind Kimi K3.1 Pro (46), matching Grok 4.7 (xhigh), and scoring 1 point below Claude Haiku 5.5 (max). Evaluation highlights: a 31% score on FrontierCode 2.0, the highest among models from Chinese labs; 50% on AA-Omniscience v1.1, but with a hallucination rate as high as 89%; pricing of $0.834/$2.501 per 1M input/output tokens; and support for a 1M-token context window and text and image inputs.
Also reported by 1 other source
- Tencent Hunyuan Hy4 scores 35 on Artificial Analysis Intelligence Index v5, ranking second among models from Chinese AI labsArtificial Analysis · 11 days ago
Source: Tencent Hunyuan · x.com
Event follow-up2
View all event coverage- Tencent Hunyuan thanks Artificial Analysis for its Hy4 evaluation; model scores 35 on Intelligence Index v5Tencent Hunyuan · 11 days ago
- Google DeepMind releases Gemini 4 Carbon, a frontier modelGoogle DeepMind:Blog · 19 days ago