{"slug": "vibethinker-3b-achieves-80-2-on-lcbv6", "title": "VibeThinker-3B achieves 80.2 on LCBv6", "summary": "VibeThinker-3B, a dense 3B parameter model, achieves 80.2 Pass@1 on LCB v6, 94.3 on AIME'26, and 76.4 on IMO-AnsBench, with further improvements using CLR. The model demonstrates frontier-level verifiable reasoning and OOD coding performance, challenging traditional scaling laws.", "body_md": "⭐ VibeThinker-3B is released — a dense 3B model for frontier-level verifiable reasoning.\n🚀 Reasoning: 94.3 on AIME’26, 76.4 on IMO-AnsBench, and 80.2 Pass@1 on LCB v6; with CLR, AIME‘26 improves to 97.1 and IMO-AnsBench to 80.6.\n💻 OOD Coding: On recent unseen LeetCode weekly B passes 123/128 (96.1%) first-attempt Python submissions.\n⚡ Efficiency: Only 3B parameters, yet reaching the performance range of much larger top-tier reasoning models.\n🧠 Perspective: Small models are not just cheaper substitutes. In parameter-dense domains with clear verification signals, SLMs offer a path to frontier-level reasoning that complements traditional Scaling Law.\nModel :", "url": "https://wpnews.pro/news/vibethinker-3b-achieves-80-2-on-lcbv6", "canonical_source": "https://twitter.com/WeiboLLM/status/2066870851841274249", "published_at": "2026-06-16 21:08:26+00:00", "updated_at": "2026-06-16 21:18:34.604813+00:00", "lang": "en", "topics": ["large-language-models", "ai-research", "ai-products"], "entities": ["VibeThinker-3B", "LCB v6", "AIME'26", "IMO-AnsBench", "CLR", "LeetCode"], "alternates": {"html": "https://wpnews.pro/news/vibethinker-3b-achieves-80-2-on-lcbv6", "markdown": "https://wpnews.pro/news/vibethinker-3b-achieves-80-2-on-lcbv6.md", "text": "https://wpnews.pro/news/vibethinker-3b-achieves-80-2-on-lcbv6.txt", "jsonld": "https://wpnews.pro/news/vibethinker-3b-achieves-80-2-on-lcbv6.jsonld"}}