Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

VibeThinker-3B: Exploring the Frontier of Verifiable Reasoning in Small Language Models

About

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.

Sen Xu, Shixi Liu, Wei Wang, Jixin Min, Yingwei Dai, Zhibin Yin, Yirong Chen, Xin Zhou, Junlin Zhang• 2026

Related benchmarks

TaskDatasetResultRank
Mathematical ReasoningAIME 2025
Accuracy96.7
378
Mathematical ReasoningHMMT 2025
Accuracy95.4
241
Mathematical ReasoningBRUMO25
Accuracy99.2
89
Knowledge ReasoningGPQA Diamond
Accuracy72.9
48
Instruction FollowingIFBench
Accuracy74.5
41
Mathematics ReasoningAIME 2025
AIME 2025 Accuracy96.7
18
CodingLCB v6
Accuracy80.2
16
Mathematical ReasoningAIME 2026
Accuracy97.1
16
Mathematical ReasoningIMO-AnswerBench
Accuracy80.6
16
Mathematics ReasoningIMO-Ans
Accuracy80.6
15
Showing 10 of 16 rows

Other info

GitHub

Follow for update