| DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning | Jan 22, 2025 | Mathematical ReasoningMulti-task Language Understanding | CodeCode Available | 15 | 5 |
| Qwen3 Technical Report | May 14, 2025 | Code GenerationMathematical Reasoning | CodeCode Available | 13 | 5 |
| Qwen2.5 Technical Report | Dec 19, 2024 | Common Sense Reasoning | CodeCode Available | 13 | 5 |
| Absolute Zero: Reinforced Self-play Reasoning with Zero Data | May 6, 2025 | Mathematical Reasoning | CodeCode Available | 11 | 5 |
| DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models | Feb 5, 2024 | Arithmetic ReasoningMath | CodeCode Available | 9 | 5 |
| NeedleBench: Can LLMs Do Retrieval and Reasoning in Information-Dense Context? | Jul 16, 2024 | 4k8k | CodeCode Available | 9 | 5 |
| s1: Simple test-time scaling | Jan 31, 2025 | Language ModelingLanguage Modelling | CodeCode Available | 9 | 5 |
| DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence | Jun 17, 2024 | 16kLanguage Modeling | CodeCode Available | 9 | 5 |
| O1 Replication Journey -- Part 2: Surpassing O1-preview through Simple Distillation, Big Progress or Bitter Lesson? | Nov 25, 2024 | HallucinationKnowledge Distillation | CodeCode Available | 7 | 5 |
| EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty | Jan 26, 2024 | Code GenerationInstruction Following | CodeCode Available | 7 | 5 |
| Skywork-R1V3 Technical Report | Jul 8, 2025 | cross-modal alignmentMathematical Reasoning | CodeCode Available | 7 | 5 |
| Training Compute-Optimal Large Language Models | Mar 29, 2022 | AnachronismsAnalogical Similarity | CodeCode Available | 6 | 5 |
| Sparks of Artificial General Intelligence: Early experiments with GPT-4 | Mar 22, 2023 | Arithmetic ReasoningMathematical Reasoning | CodeCode Available | 6 | 5 |
| Gorilla: Large Language Model Connected with Massive APIs | May 24, 2023 | HallucinationLanguage Modeling | CodeCode Available | 6 | 5 |
| Mistral 7B | Oct 10, 2023 | answerability predictionArithmetic Reasoning | CodeCode Available | 6 | 5 |
| LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning | Oct 3, 2024 | Efficient ExplorationMathematical Problem-Solving | CodeCode Available | 5 | 5 |
| DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning | May 20, 2025 | HallucinationMathematical Reasoning | CodeCode Available | 5 | 5 |
| LIMO: Less is More for Reasoning | Feb 5, 2025 | MathMathematical Reasoning | CodeCode Available | 5 | 5 |
| Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8B | Jun 11, 2024 | Decision MakingGSM8K | CodeCode Available | 5 | 5 |
| Kimi-VL Technical Report | Apr 10, 2025 | Long-Context UnderstandingMathematical Reasoning | CodeCode Available | 5 | 5 |
| Search-o1: Agentic Search-Enhanced Large Reasoning Models | Jan 9, 2025 | Code Generation | CodeCode Available | 5 | 5 |
| R-KV: Redundancy-aware KV Cache Compression for Training-Free Reasoning Models Acceleration | May 30, 2025 | Mathematical Reasoning | CodeCode Available | 5 | 5 |
| Group-in-Group Policy Optimization for LLM Agent Training | May 16, 2025 | GPUMathematical Reasoning | CodeCode Available | 5 | 5 |
| DeepSeek-Prover-V2: Advancing Formal Mathematical Reasoning via Reinforcement Learning for Subgoal Decomposition | Apr 30, 2025 | Automated Theorem ProvingLarge Language Model | CodeCode Available | 5 | 5 |
| WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct | Aug 18, 2023 | Arithmetic ReasoningGSM8K | CodeCode Available | 5 | 5 |
