VibeThinker-3B：探索小型语言模型中可验证推理的边界
VibeThinker-3B: Exploring the Frontier of Verifiable Reasoning in Small Language Models
摘要
这份技术报告介绍了VibeThinker-3B模型。该模型属于紧凑型、高参数密度模型，拥有3B个参数。其开发目的是探索在严格限制模型规模的情况下，可验证推理能力的极限表现。基于“从频谱到信号”的模型训练范式，我们通过一系列优化措施来提升模型的性能，包括基于课程设计的监督式微调、多领域强化学习以及离线自蒸馏等技术。实验结果表明，VibeThinker-3B在要求极高的可验证任务上取得了领先的性能表现。具体来说，它在AIME26测试上的得分达到了94.3；在LiveCodeBench v6测试上的Pass@1得分为80.2；在最近未接触过的LeetCode竞赛中，其接受率高达96.1%。这些成绩使其性能跻身一流推理系统的行列，甚至超过了那些参数数量多几倍的旗舰模型，如DeepSeek V3.2、GLM-5和Gemini 3 Pro。此外，在IFEval测试中的得分达到93.4，这表明这种极端的推理能力提升并不会影响模型的严格指令控制能力。作为之前1.5B参数模型的发展延续，这些发现为“参数压缩与参数覆盖假设”提供了依据。该假设认为，可验证推理可以被压缩成紧凑型的推理核心，而开放域知识和通用能力则需要通过广泛的参数覆盖来实现。这一观点表明，紧凑型模型不仅仅是高效的替代方案，而是实现前沿性能水平的有效途径。
English Abstract
This technical report introduces VibeThinker-3B, a compact dense model with 3B parameters developed to investigate how far verifiable reasoning can be pushed within a strictly small-model regime. Building upon the Spectrum-to-Signal post-training paradigm, we systematically enhance the model through an optimized pipeline that includes curriculum-based supervised fine-tuning, multi-domain reinforcement learning, and offline self-distillation. Experimental evaluations demonstrate that VibeThinker-3B achieves frontier-level performance on highly demanding verifiable tasks. Specifically, it attains a score of 94.3 on AIME26 (improving to 97.1 with claim-level test-time scaling), an 80.2 Pass@1 on LiveCodeBench v6, and exhibits strong out-of-distribution generalization with a 96.1\% acceptance rate on recent unseen LeetCode contests. This effectively places it in the performance band of first-tier reasoning systems, matching or exceeding flagship models that are orders of magnitude larger, such as DeepSeek V3.2, GLM-5, and Gemini 3 Pro. Furthermore, a score of 93.4 on IFEval confirms that this extreme reasoning enhancement does not compromise strict instruction controllability. Extending our previous 1.5B work, these findings motivate the Parametric Compression-Coverage Hypothesis, which views verifiable reasoning as compressible into compact reasoning cores, while open-domain knowledge and general-purpose competence require broad parameter coverage over facts, concepts, and long-tail scenarios. This perspective suggests that compact models are not merely deployment-efficient substitutes, but a complementary path toward frontier-level performance in parameter-dense capability regimes.