mlsanityData to 7 Oct 2026

Hermes 4 Technical Report

arXiv 2508.18255 ↗First posted 25 Aug 2025cs.AIcited by 5

On the map: LLM reasoning → Mathematical reasoning

Abstract (arXiv)

We present Hermes 4, a family of hybrid reasoning models that combine structured, multi-turn reasoning with broad instruction-following ability. We describe the challenges encountered during data curation, synthesis, training, and evaluation, and outline the solutions employed to address these challenges at scale. We comprehensively evaluate across mathematical reasoning, coding, knowledge, comprehension, and alignment benchmarks, and we report both quantitative performance and qualitative behavioral analysis. To support open research, all model weights are published publicly at https://huggingface.co/collections/NousResearch/hermes-4-collection-68a731bfd452e20816725728

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Placed in Mathematical reasoning, one of 17 directions in LLM reasoning. Builds on 34 of its 57 references that are in the map. First posted on arXiv 25 Aug 2025.

Builds on

34 of 57 references.

References · 34

  1. 2025Qwen3 Technical Reportcited by 8,195
  2. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  3. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  4. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  5. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,748
  6. 2018Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answeringcited by 2,114
  7. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,970
  8. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 1,906
  9. 2024MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmarkcited by 1,758
  10. 2023Instruction-Following Evaluation for Large Language Modelscited by 1,143
  11. 2023SGLang: Efficient Execution of Structured Language Model Programscited by 1,107
  12. 2024The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scalecited by 1,104
22 more
  1. 2022STaR: Bootstrapping Reasoning With Reasoningcited by 895
  2. 2019DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphscited by 883
  3. 2024LLM Evaluators Recognize and Favor Their Own Generationscited by 651
  4. 2024Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inferencecited by 527
  5. 2024From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipelinecited by 484
  6. 2024Scaling Synthetic Data Creation with 1,000,000,000 Personascited by 397
  7. 2024DataComp-LM: In search of the next generation of training sets for language modelscited by 381
  8. 2024Measuring short-form factuality in large language modelscited by 345
  9. 2025DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoningcited by 261
  10. 2025FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Servingcited by 248
  11. 2024Flex Attention: A Programming Model for Generating Optimized Attention Kernelscited by 180
  12. 2025Generalizing Verifiable Instruction Followingcited by 178
  13. 2024Generative Reward Modelscited by 148
  14. 2025General-Reasoner: Advancing LLM Reasoning Across All Domainscited by 132
  15. 2025NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Modelcited by 94
  16. 2024AgentInstruct: Toward Generative Teaching with Agentic Flowscited by 88
  17. 2024TorchTitan: One-stop PyTorch native solution for production ready LLM pre-trainingcited by 80
  18. 2023EQ-Bench: An Emotional Intelligence Benchmark for Large Language Modelscited by 75
  19. 2025Magistralcited by 57
  20. 2024Collapse or Thrive? Perils and Promises of Synthetic Data in a Self-Generating Worldcited by 49
  21. 2025rStar-Coder: Scaling Competitive Code Reasoning with a Large-Scale Verified Datasetcited by 49
  22. 2024How to Synthesize Text Data without Model Collapse?cited by 24

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026AI Research Agents Narrow Scientific Explorationcited by 2
  2. 2026Measuring and Eliminating Refusals in Military Large Language Modelscited by 0
  3. 2026ShardMeter: Sharded and Geo-Distributed Training Without the Guessworkcited by 0
  4. 2026SiliconBench: Speed, Memory, and Fidelity for LLM Serving on Unified-Memory Desktopscited by 0
  5. 2026Collaborative Reasoning Distillation via Cross-Feedback and Coherent Curationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025HERMES: Towards Efficient and Verifiable Mathematical Reasoning in LLMs
  2. 2025Reasoning Relay: Evaluating Stability and Interchangeability of Large Language Models in Mathematical Reasoning
  3. 2026Mathematical Reasoning in Large Language Models: Benchmarks, Architectures, Evaluation, and Open Challenges
  4. 2025Catch Me If You Can: How Smaller Reasoning Models Pretend to Reason with Mathematical Fidelity
  5. 2025FINEREASON: Evaluating and Improving LLMs' Deliberate Reasoning through Reflective Puzzle Solving
  6. 2026LiveMathematicianBench: A Live Benchmark for Research-Level Mathematical Reasoning with Proof Sketches
  7. 2026MIRA-Math: A Benchmark for Minimal Information Requesting and Mathematical Reasoning
  8. 2024Functional Benchmarks for Robust Evaluation of Reasoning Performance, and the Reasoning Gap