Tencent: Hunyuan A13B Instruct

● Excellent

by Tencent Open Weight Intelligent Rank #58 of 87

8.2
/ 10

Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thought. It offers competitive benchmark...

Choose a model to compare against Tencent: Hunyuan A13B Instruct

Specifications

Specifications for Tencent: Hunyuan A13B Instruct
AttributeValue
Lab Tencent
Tags Open Weight Intelligent
Overall Score 8.2/10
Release Date 2025-07
Context Window 131,072 tokens
Input Price / 1M $0.14
Output Price / 1M $0.57
Input Modalities Text
Output Modalities Text

Strengths

  • 80B total parameters with 13B active (Mixture-of-Experts)
  • Built-in Chain-of-Thought reasoning support
  • Competitive benchmark performance for its size class
  • Budget pricing at $0.14/$0.57 per 1M tokens
  • Tencent-backed model with strong Chinese language support

Weaknesses

  • Lower active parameters (13B) limits peak reasoning depth
  • Smaller ecosystem and community vs Qwen/DeepSeek alternatives
  • Limited English-centric benchmarks available

Best For

  • Cost-sensitive Chinese-language applications
  • General reasoning with Chain-of-Thought
  • Open-weight deployment and fine-tuning
  • Enterprise use cases in Tencent ecosystem

Sources & Further Reading

Related Models

Scores are aggregated from public benchmarks (MMLU, HumanEval, MATH, GSM8K, LMSYS) and normalized to a 1–10 scale. Methodology →