← All notes

Tulu 3: Pushing Frontiers in Open Language Model Post-Training

Summary

Tulu 3 is a family of fully open post-trained models, released with data, code, and training recipes, built on Llama 3.1 base models. The training algorithms include supervised finetuning (SFT), Direct Preference Optimization (DPO), and Reinforcement Learning with Verifiable Rewards (RLVR). The authors also introduce a multi-task evaluation scheme with development and unseen evaluations and substantial decontamination of existing open datasets. [S1]

Claims

Verification

When to apply

Use when you need an open post-training stack that combines SFT, DPO, and verifiable-reward RL.

Facts

Sources

License: this note is CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Summary by iinventedlight (AI-assisted). Paper is CC BY 4.0.

License: CC-BY-4.0 · Summary by iinventedlight (AI-assisted). Source: Nathan Lambert, Jacob Morrison, Valentina Pyatkin, and 20 coauthors (listed on the arXiv abs page), Tulu 3: Pushing Frontiers in Open Language Model Post-Training (CC BY 4.0).

Cite this

Permanent ID: iil:note:kww5wzkw

'iinventedlight (AI-assisted)'. 2026. "Tulu 3: Pushing Frontiers in Open Language Model Post-Training." iinventedlight Library, iil:note:kww5wzkw, version of 2026-11-12. https://iinventedlight.com/library/notes/2411-15124-tulu-3/. License: CC-BY-4.0.

@misc{iil_note_kww5wzkw,
  author = {{'iinventedlight (AI-assisted)'}},
  title = {{Tulu 3: Pushing Frontiers in Open Language Model Post-Training}},
  howpublished = {iinventedlight Library},
  year = {2026},
  date = {2026-11-12},
  url = {https://iinventedlight.com/library/notes/2411-15124-tulu-3/},
  note = {Permanent ID iil:note:kww5wzkw. License: CC-BY-4.0.},
}

Markdown

Spotted a mistake? Use the MCP feedback tool or email hello@iinventedlight.com.

For language models and agents: start at /llms.txt | /agents.md | /.well-known/agent-library.json. This page in Markdown: /library/notes/2411-15124-tulu-3.md.