This model is a fine-tuned version of Qwen/Qwen2.5-7B-Instruct on the OpenThoughts3-1.2M dataset. It represents a notable improvement over our previous models, OpenThinker-7B and OpenThinker2-7B, and it outperforms several other strong reasoning 7B models such as DeepSeek-R1-Distill-Qwen-7B and Llama-3.1-Nemotron-Nano-8B-v1, despite being trained only with SFT, without any RL.

This time, we also released a paper! See our paper and blog post for more details. OpenThinker3-32B to follow! 👀

Evaluation Results

The numbers reported in the table below are evaluated with our open-source tool Evalchemy. In the table below, we bold values in each column that are within 2 standard errors of the best.

Model	Data	AIME24	AIME25	AMC23	MATH500	HMMT O2/25	LCB 06/24-01/25	CodeElo	CodeForces	GPQA-D	JEEBench
OpenThinker-7B	✅	30.7	22.0	72.5	82.8	15.7	26.1	11.1	14.9	38.6	45.3
OpenThinker2-7B	✅	60.7	38.7	89.8	87.6	24.7	40.6	22.8	26.6	47.0	65.1
OpenThinker3-7B	✅	69.0	53.3	93.5	90.0	42.7	51.7	31.0	32.2	53.7	72.4
DeepSeek-R1-Distill-Qwen-32B	❌	51.3	38.0	92.0	88.0	25.0	34.5	19.9	21.1	33.2	50.4
OpenR1-Distill-7B	✅	57.7	39.7	87.0	88.0	25.7	30.7	30.1	29.3	58.9	68.7
Llama-3.1-Nemotron-Nano-8B-v1	✅	62.0	48.0	94.0	89.4	26.7	50.9	30.9	32.9	52.9	70.7
AceReason-Nemotron-7B	✅	71.0	50.7	93.8	89.8	33.3	44.3	32.9	30.9	52.9	64.3

Data

This model was trained on the OpenThoughts3-1.2M dataset.

The key to the strong model performance is our comprehensive data pipeline and over 1,000+ ablation experiments. This led to the creation of OpenThoughts3-1.2M, which consists of 850,000 math questions, 250,000 code questions, and 100,000 science questions. Reasoning traces are generated with QwQ-32B.

See the OpenThoughts3-1.2M dataset page or our paper for additional information.

Intended uses & limitations

Apache 2.0 License

Training procedure

We used 512 A100 nodes to train the model for 48 hours.

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 8e-05
seed: 42
distributed_type: multi-GPU
num_devices: 512
gradient_accumulation_steps: 1
total_train_batch_size: 512
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 5.0
weight_decay: 0.0

Framework versions

Transformers 4.46.1
Pytorch 2.3.0
Datasets 3.1.0
Tokenizers 0.20.3

More info can be found in our repository: https://github.com/open-thoughts/open-thoughts.

Citation

@misc{guha2025openthoughtsdatarecipesreasoning,
  title={OpenThoughts: Data Recipes for Reasoning Models}, 
  author={Etash Guha and Ryan Marten and Sedrick Keh and Negin Raoof and Georgios Smyrnis and Hritik Bansal and Marianna Nezhurina and Jean Mercat and Trung Vu and Zayne Sprague and Ashima Suvarna and Benjamin Feuer and Liangyu Chen and Zaid Khan and Eric Frankel and Sachin Grover and Caroline Choi and Niklas Muennighoff and Shiye Su and Wanjia Zhao and John Yang and Shreyas Pimpalgaonkar and Kartik Sharma and Charlie Cheng-Jie Ji and Yichuan Deng and Sarah Pratt and Vivek Ramanujan and Jon Saad-Falcon and Jeffrey Li and Achal Dave and Alon Albalak and Kushal Arora and Blake Wulfe and Chinmay Hegde and Greg Durrett and Sewoong Oh and Mohit Bansal and Saadia Gabriel and Aditya Grover and Kai-Wei Chang and Vaishaal Shankar and Aaron Gokaslan and Mike A. Merrill and Tatsunori Hashimoto and Yejin Choi and Jenia Jitsev and Reinhard Heckel and Maheswaran Sathiamoorthy and Alexandros G. Dimakis and Ludwig Schmidt},
  year={2025},
  eprint={2506.04178},
  archivePrefix={arXiv},
  primaryClass={cs.LG},
  url={https://arxiv.org/abs/2506.04178}, 
}

bernquant/OpenThinker3-7B

OpenThinker3-7B