Olmo-3.1-32B-Instruct
A 32B instruction-tuned model from Ai2, built for reasoning, coding, and instruction-following, and released as a fully open model with public code, checkpoints, and training data.
Olmo-3.1-32B-Instruct
Summary
Introduction
Ai2 introduces Olmo 3, a new family of 7B and 32B models available in both Instruct and Think variants. Long chain-of-thought reasoning improves performance on tasks like math and coding. Olmo is a series of open language models designed to enable the science of language models. These models are pre-trained on the Dolma 3 dataset and post-trained on the Dolci datasets. Ai2 is releasing all code, checkpoints, logs (coming soon), and associated training details.
The core models released in this batch include the following:
| Stage | Olmo 3 7B Think | Olmo (3/3.1) 32B Think | Olmo 3 7B Instruct | Olmo 3.1 32B Instruct |
|---|---|---|---|---|
| Base Model | Olmo-3-7B | Olmo-3-32B | Olmo-3-7B | Olmo-3-32B |
| SFT | Olmo-3-7B-Think-SFT | Olmo-3-32B-Think-SFT | Olmo-3-7B-Instruct-SFT | Olmo-3.1-32B-Instruct-SFT |
| DPO | Olmo-3-7B-Think-DPO | Olmo-3-32B-Think-DPO | Olmo-3-7B-Instruct-DPO | Olmo-3.1-32B-Instruct-DPO |
| Final Models (RLVR) | Olmo-3-7B-Think | Olmo-3-32B-Think Olmo-3.1-32B-Think | Olmo-3-7B-Instruct | Olmo-3.1-32B-Instruct |
Model Description
- Developed by: Allen Institute for AI (Ai2)
- Model type: a Transformer style autoregressive language model.
- Language(s) (NLP): English
- License: This model is licensed under Apache 2.0. It is intended for research and educational use in accordance with Ai2's Responsible Use Guidelines.
- Contact: Technical inquiries:
[email protected]. Press:[email protected] - Date cutoff: Dec. 2024.
Model Sources
- Project Page: https://allenai.org/olmo
- Repositories:
- Open-Instruct for DPO and RLVR: https://github.com/allenai/open-instruct
- OLMo-Core for pre-training and SFT: https://github.com/allenai/OLMo-core
- OLMo-Eval for evaluation: https://github.com/allenai/OLMo-Eval
- Paper: https://allenai.org/papers/olmo3
Evaluation
| Metric | Olmo 3.1 32B Instruct SFT | Olmo 3.1 32B Instruct DPO | Olmo 3.1 32B Instruct | Apertus 70B | Qwen 3 32B (No Think) | Qwen 3 VL 32B Instruct | Qwen 2.5 32B | Gemma 3 27B | Gemma 2 27B | OLMo 2 32B |
|---|---|---|---|---|---|---|---|---|---|---|
| Math | ||||||||||
| MATH | 74.4 | 86.6 | 93.4 | 36.2 | 84.3 | 95.1 | 80.2 | 87.4 | 51.5 | 49.2 |
| AIME 2024 | 12.7 | 35.2 | 67.8 | 0.31 | 27.9 | 75.4 | 15.7 | 28.9 | 4.7 | 4.6 |
| AIME 2025 | 8.2 | 23.3 | 57.9 | 0.1 | 21.3 | 64.2 | 13.4 | 22.9 | 0.9 | 0.9 |
| OMEGA | 15.5 | 33.3 | 42.2 | 5.6 | 23.4 | 44.0 | 19.2 | 24.0 | 9.1 | 9.8 |
| Reasoning | ||||||||||
| BigBenchHard | 69.0 | 82.1 | 84.0 | 57.0 | 80.4 | 89.0 | 80.9 | 82.4 | 66.0 | 65.6 |
| ZebraLogic | 30.6 | 51.1 | 61.7 | 9.0 | 28.4 | 86.7 | 24.1 | 24.8 | 17.2 | 13.3 |
| AGI Eval English | 71.7 | 79.4 | 79.5 | 61.6 | 82.4 | 89.4 | 78.9 | 76.9 | 70.9 | 68.4 |
| Coding | ||||||||||
| HumanEvalPlus | 80.8 | 85.7 | 86.7 | 42.9 | 83.9 | 89.3 | 82.6 | 79.2 | 67.5 | 44.4 |
| MBPP+ | 61.5 | 63.6 | 65.1 | 45.8 | 67.9 | 69.0 | 66.6 | 65.7 | 61.2 | 49.0 |
| LiveCodeBench v3 | 35.4 | 49.6 | 54.7 | 9.7 | 57.5 | 70.2 | 49.9 | 39.0 | 28.7 | 10.6 |
| IF | ||||||||||
| IFEval | 87.7 | 87.3 | 88.8 | 70.4 | 87.5 | 88.1 | 81.9 | 85.4 | 62.1 | 85.8 |
| IFBench | 29.7 | 36.3 | 39.7 | 26.0 | 31.3 | 37.2 | 36.7 | 31.3 | 27.8 | 36.4 |
| Knowledge & QA | ||||||||||
| MMLU | 79.0 | 81.9 | 80.9 | 70.2 | 85.8 | 88.7 | 84.6 | 74.6 | 76.1 | 77.1 |
| PopQA | 23.7 | 28.5 | 25.0 | 33.5 | 25.9 | 25.7 | 28.0 | 30.2 | 30.4 | 37.2 |
| GPQA | 41.3 | 47.9 | 48.6 | 27.9 | 54.4 | 61.4 | 44.6 | 45.0 | 39.9 | 36.4 |
| Chat | ||||||||||
| AlpacaEval 2 LC | 42.2 | 69.7 | 59.8 | 19.9 | 67.9 | 84.3 | 81.9 | 65.5 | 39.8 | 38.0 |
| Safety | 92.1 | 88.9 | 89.5 | 77.1 | 81.6 | 85.8 | 82.2 | 68.8 | 74.4 | 84.2 |
Parameters
Inputs
prompt- (text): The input text provided by the user. This can be a question, instruction, or any natural language prompt that the model will use to generate a response.
max_new_tokens- (integer): The maximum number of tokens the model is allowed to generate in the response. Higher values allow longer outputs but may increase latency and cost.top_k- (integer): Limits the sampling pool to the top k most likely next tokens at each step. Lower values make the output more deterministic, while higher values increase diversity.top_p- (float): Controls nucleus (probability) sampling. The model selects tokens from the smallest set whose cumulative probability is at least p. Lower values make outputs more focused; higher values increase randomness and creativity.
Output
output- (text): The generated text response from the model, based on the provided prompt and sampling parameters.
Usage for developers
Please find below the details to track the information and access the code for processing the model on our platform.
Requirements
pip install -r requirements.txt
Code based on AIOZ structure
from transformers import AutoModelForCausalLM, AutoTokenizer
...
def do_ai_task(
prompt: str,
max_new_tokens: int ,
top_k: int ,
top_p: float ,
model_storage_directory: Union[str, Path],
device: Literal["cpu", "cuda", "gpu"] = "cpu",
*args, **kwargs) -> Any:
"""Define AI task: load model, pre-process, post-process, etc ..."""
# Define AI task workflow. Below is an example
model_weights_path = Path(model_storage_directory) / "Olmo-3.1-32B-Instruct"
olmo = AutoModelForCausalLM.from_pretrained(model_weights_path)
tokenizer = AutoTokenizer.from_pretrained(model_weights_path)
...
output_ = tokenizer.batch_decode(response, skip_special_tokens=True)[0]
return output_
Reference
This repository is based on and inspired by Ai2's Olmo project, including its open code, checkpoints, and training details. We sincerely appreciate their generosity in sharing the model and its full training pipeline.
License
Olmo 3.1 32B Instruct is released by the Allen Institute for AI (Ai2) under the Apache License 2.0, which permits use, modification, and redistribution for both commercial and non-commercial purposes. Ai2 additionally asks that the model be used in accordance with its Responsible Use Guidelines. AIOZ AI redistributes this model under the Apache 2.0 terms. A full copy of the license is included in the LICENSE file, and attribution is provided in the NOTICE file.
Citation
@misc{olmo2025olmo3,
title={Olmo 3},
author={Team Olmo and Allyson Ettinger and Amanda Bertsch and Bailey Kuehl and David Graham and David Heineman and Dirk Groeneveld and Faeze Brahman and Finbarr Timbers and Hamish Ivison and Jacob Morrison and Jake Poznanski and Kyle Lo and Luca Soldaini and Matt Jordan and Mayee Chen and Michael Noukhovitch and Nathan Lambert and Pete Walsh and Pradeep Dasigi and Robert Berry and Saumya Malik and Saurabh Shah and Scott Geng and Shane Arora and Shashank Gupta and Taira Anderson and Teng Xiao and Tyler Murray and Tyler Romero and Victoria Graf and Akari Asai and Akshita Bhagia and Alexander Wettig and Alisa Liu and Aman Rangapur and Chloe Anastasiades and Costa Huang and Dustin Schwenk and Harsh Trivedi and Ian Magnusson and Jaron Lochner and Jiacheng Liu and Lester James V. Miranda and Maarten Sap and Malia Morgan and Michael Schmitz and Michal Guerquin and Michael Wilson and Regan Huff and Ronan Le Bras and Rui Xin and Rulin Shao and Sam Skjonsberg and Shannon Zejiang Shen and Shuyue Stella Li and Tucker Wilde and Valentina Pyatkin and Will Merrill and Yapei Chang and Yuling Gu and Zhiyuan Zeng and Ashish Sabharwal and Luke Zettlemoyer and Pang Wei Koh and Ali Farhadi and Noah A. Smith and Hannaneh Hajishirzi},
year={2025},
eprint={2512.13961},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2512.13961},
}