Hy3
설명
Hy3 is a 295B-parameter Mixture-of-Experts (MoE) model with 21B active parameters and a 3.8B MTP layer, developed by the Tencent Hy Team. Following the Hy3 Preview launch in late April, the team scaled up post-training with higher-quality data and RL, gathering feedback from 50+ products. Hy3 outperforms similar-size models and rivals flagship open-source models with 2-5x the parameters, with strong gains in reasoning, agentic, and long-context tasks. It uses 80 layers (plus 1 MTP layer), 64 GQA attention heads (8 KV heads, head dim 128), a 4096 hidden size, 192 experts with top-8 activated, a 256K context window, and BF16 precision. Hy3 is a hybrid-thinking model supporting configurable reasoning effort (no_think, low, high), and emphasizes production-grade tool-call and output-format stability, reduced hallucination, and reliable multi-turn intent tracking.
능력 레이더
전용 과학 벤치마크가 없을 때 Science는 LLM Stats 과학 점수 또는 추론 능력에서 추정합니다.
랭킹
| 도메인 | #순위 | 점수 | 소스 |
|---|---|---|---|
| 에이전트형 역량 | 68 | 48.0 | LS |
벤치마크 점수 (LLM Stats)
(LLM Stats (zeroeval))Agents
Chemistry
Code
Math
Physics
Reasoning
Search
AA 평가 지수
(Artificial Analysis)AA 평가 데이터가 없습니다
LLM Stats 카테고리 점수
(LLM Stats (zeroeval))가격
속도
공급자 가격 순위
공급자 가격 순위
18개 공급자
이 모델의 다양한 API 공급자 간 가격 비교.