{"slug": "150m-parameter-reasoning-model-sets-new-cost-accuracy-frontier-on-arc-agi-1", "title": "150M-parameter reasoning model sets new cost-accuracy frontier on ARC-AGI-1", "summary": "Thinking Machines' 150M-parameter BDH-CQ reasoning model, which combines in-context learning with recurrent latent reasoning, achieves 29.5% pass@2 on the public ARC-AGI-1 evaluation set at a computed inference cost of $0.0007 per task, breaking the previously reported cost-accuracy Pareto frontier and establishing a new state of the art in benchmark cost efficiency.", "body_md": "Collection Papers that made me appreciate my major and my life a little more. obs=Observation, innov=Innovation. Most papers are abt improving tiny models. • 268 items • Updated • 65\n\n## Abstract\n\nA 150M-parameter reasoning model using recurrent latent reasoning and in-context learning achieves a new cost-accuracy frontier on ARC-AGI-1.\n\n[thinkingmachines/Inkling-Small](/thinkingmachines/Inkling-Small)\n\nWe introduce BDH-CQ, a reasoning model that combines [in-context learning](/papers?q=in-context%20learning) with [recurrent latent reasoning](/papers?q=recurrent%20latent%20reasoning). Inputs presented at inference time continuously update the model's recurrent memory; the model then solves a query through iterative computation in a [high-dimensional latent space](/papers?q=high-dimensional%20latent%20space), without verbalizing its intermediate reasoning. We evaluate the model on the public [ARC-AGI-1](/papers?q=ARC-AGI-1) evaluation set and use controlled ARC-like interventions to study what it learns from demonstrations, how consistently it applies an inferred transformation, and which concepts remain difficult. A 150M-parameter configuration reaches 29.5% pass@2 at a computed inference cost of \\$0.0007 per task. This operating point breaks through the previously reported [ARC-AGI-1](/papers?q=ARC-AGI-1) [cost-accuracy Pareto frontier](/papers?q=cost-accuracy%20Pareto%20frontier), establishing a new state of the art in benchmark cost efficiency.\n\n### Community\n\nThis is an automated message from the [Librarian Bot](https://huggingface.co/librarian-bots). I found the following papers similar to this paper.\n\nThe following papers were recommended by the Semantic Scholar API\n\n[Penelope: Localized Latent Recurrence for Efficient Structured Reasoning](https://huggingface.co/papers/2607.25915)(2026)[Recursive Vision Language Models for General Symbolic Reasoning](https://huggingface.co/papers/2608.01534)(2026)[DiscoLoop: Looping Discrete Embeddings and Continuous Hidden States for Multi-hop Reasoning](https://huggingface.co/papers/2607.00341)(2026)[J-CoT: Chain-of-Thought in J-Space](https://huggingface.co/papers/2607.21981)(2026)[Learning to Refine Hidden States for Reliable LLM Reasoning](https://huggingface.co/papers/2606.17524)(2026)[Bridging the Gap Between Latent and Explicit Reasoning with Looped Transformers](https://huggingface.co/papers/2606.31779)(2026)[What Survives When You Compress a Recursive Reasoner for the Edge?](https://huggingface.co/papers/2606.26488)(2026)\n\nPlease give a thumbs up to this comment if you found it helpful!\n\nIf you want recommendations for any Paper on Hugging Face checkout [this](https://huggingface.co/spaces/librarian-bots/recommend_similar_papers) Space\n\nYou can directly ask Librarian Bot for paper recommendations by tagging it in a comment: `@librarian-bot recommend`\n\nGet this paper in your agent:\n\n`hf papers read 2608.09888`\n\n## Don't have the latest CLI?\n\n`curl -LsSf https://hf.co/cli/install.sh | bash`\n\n## Models citing this paper 0\n\nNo model linking this paper\n\n## Datasets citing this paper 0\n\nNo dataset linking this paper\n\n### Spaces citing this paper 0\n\nNo Space linking this paper\n\n## Collections including this paper 5\n\n[Browse 5 collections that include this paper](/collections?paper=2608.09888)", "url": "https://wpnews.pro/news/150m-parameter-reasoning-model-sets-new-cost-accuracy-frontier-on-arc-agi-1", "canonical_source": "https://huggingface.co/papers/2608.09888", "published_at": "2026-08-12 10:21:52+00:00", "updated_at": "2026-08-12 10:42:12.523353+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "ai-research"], "entities": ["Thinking Machines", "BDH-CQ", "ARC-AGI-1"], "alternates": {"html": "https://wpnews.pro/news/150m-parameter-reasoning-model-sets-new-cost-accuracy-frontier-on-arc-agi-1", "markdown": "https://wpnews.pro/news/150m-parameter-reasoning-model-sets-new-cost-accuracy-frontier-on-arc-agi-1.md", "text": "https://wpnews.pro/news/150m-parameter-reasoning-model-sets-new-cost-accuracy-frontier-on-arc-agi-1.txt", "jsonld": "https://wpnews.pro/news/150m-parameter-reasoning-model-sets-new-cost-accuracy-frontier-on-arc-agi-1.jsonld"}}