mlsanityData to 7 Oct 2026

Hunyuan-A13B Technical Report

arXiv 2609.27284 ↗First posted 23 Sep 2026cs.AIcited by 0

On the map: Mixture-of-experts → MoE large language models

Abstract (arXiv)

We present Hunyuan-A13B, an open-source large language model based on a Mixture-of-Experts architecture. It contains 80 billion total parameters but activates only 13 billion during inference, balancing model capability, computational efficiency, and deployment cost. The model is pretrained on a rigorously filtered 20T-token corpus with enhanced STEM data curation, improving factual reliability and reasoning ability. High-quality supervised fine-tuning and large-scale reinforcement learning further enhance its overall performance. Hunyuan-A13B also introduces a dual-mode Chain-of-Thought framework that adapts reasoning depth to task complexity: fast thinking for routine queries and slow thinking for complex, multi-step problems. Evaluations show competitive performance across mathematics, science, programming, general language understanding, and agent tasks, often approaching that of much larger models. Its high inference throughput makes it suitable for latency-sensitive applications. We release Hunyuan-A13B to support open research and practical LLM deployment.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in MoE large language models, one of 12 directions in Mixture-of-experts. Builds on 38 of its 59 references that are in the map. First posted on arXiv 23 Sep 2026.

Builds on

38 of 59 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025Hunyuan-TurboS: Advancing Large Language Models through Mamba-Transformer Synergy and Adaptive Chain-of-Thought21 May
  2. 2025Qwen3 Technical Report14 May
  3. 2024Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent4 Nov
  4. 2024DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models11 Jan

Other references · 34

  1. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  3. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  4. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  5. 2023Let's Verify Step by Stepcited by 3,598
  6. 2021Program Synthesis with Large Language Modelscited by 3,509
  7. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,748
  8. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,678
  9. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 1,906
  10. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Themcited by 1,767
  11. 2024MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmarkcited by 1,758
  12. 2020GLU Variants Improve Transformercited by 1,724
22 more
  1. 2023Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generationcited by 1,332
  2. 2023GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpointscited by 1,311
  3. 2024τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domainscited by 1,280
  4. 2024RULER: What's the Real Context Size of Your Long-Context Language Models?cited by 1,270
  5. 2023Instruction-Following Evaluation for Large Language Modelscited by 1,143
  6. 2024OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problemscited by 1,099
  7. 2019DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphscited by 883
  8. 2024Generative Verifiers: Reward Modeling as Next-Token Predictioncited by 465
  9. 2024LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitaskscited by 367
  10. 2023Magicoder: Empowering Code Generation with OSS-Instructcited by 251
  11. 2025ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoningcited by 186
  12. 2024Are We Done with MMLU?cited by 178
  13. 2024Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generationcited by 158
  14. 2024Generative Reward Modelscited by 148
  15. 2022MultiPL-E: A Scalable and Extensible Approach to Benchmarking Neural Code Generationcited by 132
  16. 2023CMATH: Can Your Language Model Pass Chinese Elementary School Math Test?cited by 89
  17. 2024FullStack Bench: Evaluating LLMs as Full Stack Coderscited by 56
  18. 2025ComplexFuncBench: Exploring Multi-Step and Constrained Function Calling under Long-Context Scenariocited by 53
  19. 2024McEval: Massively Multilingual Code Evaluationcited by 42
  20. 2024SysBench: Can Large Language Models Follow System Messages?cited by 26
  21. 2025A Unified Pairwise Framework for RLHF: Bridging Generative Reward Modeling and Policy Optimizationcited by 21
  22. 2025C3-Bench: The Things Real Disturbing LLM based Agent in Multi-Taskingcited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models
  2. 2025Advancing Reasoning in Large Language Models: Promising Methods and Approaches
  3. 2026Maistros: A Greek Large Language Model Adapted Through Knowledge Distillation From Large Reasoning Models
  4. 2025Hunyuan-MT Technical Report
  5. 2025Mixture of Thoughts: Learning to Aggregate What Experts Think, Not Just What They Say
  6. 2025Training Language Models to Reason Efficiently
  7. 2025Compute-Accuracy Pareto Frontiers for Open-Source Reasoning Large Language Models
  8. 2025Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models