# Olmo 3

arXiv: https://arxiv.org/abs/2512.13961 · HTML: https://mlsanity.com/paper/2512.13961/

## Key facts

- Cited by 129 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Dec 2025.

## Built on by (most cited first, 30 of 129)

- [Rethinking On-Policy Self-Distillation for Thinking Models](https://mlsanity.com/paper/2607.05184/) (2026)
- [Reasoning Models Struggle to Control their Chains of Thought](https://mlsanity.com/paper/2603.05706/) (2026)
- [Olmo Hybrid: From Theory to Practice and Back](https://mlsanity.com/paper/2604.03444/) (2026)
- [Multi-Task GRPO: Reliable LLM Reasoning Across Tasks](https://mlsanity.com/paper/2602.05547/) (2026)
- [Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information](https://mlsanity.com/paper/2605.11609/) (2026)
- [Vero: An Open RL Recipe for General Visual Reasoning](https://mlsanity.com/paper/2604.04917/) (2026)
- [Data Repetition Beats Data Scaling in Long-CoT Supervised Fine-Tuning](https://mlsanity.com/paper/2602.11149/) (2026)
- [Prompt replay: speeding up grpo with on-policy reuse of high-signal prompts](https://mlsanity.com/paper/2603.21177/) (2026)
- [Thinking Without Words: Efficient Latent Reasoning with Abstract Chain-of-Thought](https://mlsanity.com/paper/2604.22709/) (2026)
- [Decoupling the Effect of Chain-of-Thought Reasoning: A Human Label Variation Perspective](https://mlsanity.com/paper/2601.03154/) (2026)
- [Negation Neglect: When models fail to learn negations in training](https://mlsanity.com/paper/2605.13829/) (2026)
- [Can Large Language Models Understand, Reason About, and Generate Code-Switched Text?](https://mlsanity.com/paper/2601.07153/) (2026)
- [QuantLRM: Quantization of Large Reasoning Models via Fine-Tuning Signals](https://mlsanity.com/paper/2602.02581/) (2026)
- [Measuring Weak-to-Strong Legibility of Reasoning Models](https://mlsanity.com/paper/2603.20508/) (2026)
- [DeonticBench: A Benchmark for Reasoning over Rules](https://mlsanity.com/paper/2604.04443/) (2026)
- [ReasonXL: Shifting LLM Reasoning Language Without Sacrificing Performance](https://mlsanity.com/paper/2604.12378/) (2026)
- [ReasoningFlow: Discourse Structures for Understanding LLM Reasoning Traces](https://mlsanity.com/paper/2606.05402/) (2026)
- [DreamReasoner-8B: Block-Size Curriculum Learning for Diffusion Reasoning Models](https://mlsanity.com/paper/2606.19257/) (2026)
- [Automated Researchers Can Mitigate Well-characterized Alignment Failures](https://mlsanity.com/paper/2608.28945/) (2026)
- [Expected Harm: Rethinking Safety Evaluation of (Mis)Aligned LLMs](https://mlsanity.com/paper/2602.01600/) (2026)
- [Learning to Reason with Curriculum I: Provable Benefits of Autocurriculum](https://mlsanity.com/paper/2603.18325/) (2026)
- [Measuring Faithfulness Depends on How You Measure: Classifier Sensitivity in LLM Chain-of-Thought Evaluation](https://mlsanity.com/paper/2603.20172/) (2026)
- [Correct Answers from Sound Reasoning: Verifiable Process Supervision for Language Models](https://mlsanity.com/paper/2605.12519/) (2026)
- [STT-Arena: A More Realistic Environment for Tool-Using with Spatio-Temporal Dynamics](https://mlsanity.com/paper/2605.18548/) (2026)
- [Credit Assignment with Resets in Language Model Reasoning](https://mlsanity.com/paper/2605.25507/) (2026)
- [Training Reasoning Models on Saturated Problems via Failure-Prefix Conditioning](https://mlsanity.com/paper/2601.20829/) (2026)
- [Fundamental Reasoning Paradigms Induce Out-of-Domain Generalization in Language Models](https://mlsanity.com/paper/2602.08658/) (2026)
- [Large Reasoning Models Struggle to Transfer Parametric Knowledge Across Scripts](https://mlsanity.com/paper/2603.17070/) (2026)
- [Reasoning Shift: How Context Silently Shortens LLM Reasoning](https://mlsanity.com/paper/2604.01161/) (2026)
- [The Stepwise Informativeness Assumption: Why are Entropy Dynamics and Reasoning Correlated in LLMs?](https://mlsanity.com/paper/2604.06192/) (2026)

## Abstract (arXiv)

We introduce Olmo 3, a family of state-of-the-art, fully-open language models at the 7B and 32B parameter scales. Olmo 3 model construction targets long-context reasoning, function calling, coding, instruction following, general chat, and knowledge recall. This release includes the entire model flow, i.e., the full lifecycle of the family of models, including every stage, checkpoint, data point, and dependency used to build it. Our flagship model, Olmo 3 Think 32B, is the strongest fully-open thinking model released to-date.