The Allen Institute for AI (Ai2) not too long ago launched what it calls its strongest household of fashions but, Olmo 3. However the firm stored iterating on the fashions, increasing its reinforcement studying (RL) runs, to create Olmo 3.1.
The brand new Olmo 3.1 fashions concentrate on effectivity, transparency, and management for enterprises.
Ai2 up to date two of the three variations of Olmo 2: Olmo 3.1 Assume 32B, the flagship mannequin optimized for superior analysis, and Olmo 3.1 Instruct 32B, designed for instruction-following, multi-turn dialogue, and power use.
Olmo 3 has a 3rd model, Olmo 3-Base for programming, comprehension, and math. It additionally works effectively for proceed fine-tuning.
Ai2 mentioned that to improve Olmo 3 Assume 32B to Olmo 3.1, its researchers prolonged its greatest RL run with an extended coaching schedule.
“After the original Olmo 3 launch, we resumed our RL training run for Olmo 3 32B Think, training for an additional 21 days on 224 GPUs with extra epochs over our Dolci-Think-RL dataset,” Ai2 mentioned in a weblog submit. “This yielded Olmo 3.1 32B Think, which brings substantial gains across math, reasoning, and instruction-following benchmarks: improvements of 5+ points on AIME, 4+ points on ZebraLogic, 4+ points on IFEval, and 20+ points on IFBench, alongside stronger performance on coding and complex multi-step tasks.”
To get to Olmo 3.1 Instruct, Ai2 mentioned its researchers utilized the recipe behind the smaller Instruct dimension, 7B, to the bigger mannequin.
Olmo 3.1 Instruct 32B is "optimized for chat, software use, & multi-turn dialogue—making it a way more performant sibling of Olmo 3 Instruct 7B and prepared for real-world functions,” Ai2 mentioned in a submit on X.
For now, the brand new checkpoints can be found on the Ai2 Playground or Hugging Face, with API entry coming quickly.
Higher efficiency on benchmarks
The Olmo 3.1 fashions carried out effectively on benchmark assessments, predictably beating the Olmo 3 fashions.
Olmo 3.1 Assume outperformed Qwen 3 32B fashions within the AIME 2025 benchmark and carried out near Gemma 27B.
Olmo 3.1 Instruct carried out strongly towards its open-source friends, even beating fashions like Gemma 3 on the Math benchmark.
“As for Olmo 3.1 32B Instruct, it’s a larger-scale instruction-tuned model built for chat, tool use, and multi-turn dialogue. Olmo 3.1 32B Instruct is our most capable fully open chat model to date and — in our evaluations — the strongest fully open 32B-scale instruct model,” the corporate mentioned.
Ai2 additionally upgraded its RL-Zero 7B fashions for math and coding. The corporate mentioned on X that each fashions benefited from longer and extra steady coaching runs.
Dedication to transparency and open supply
Ai2 beforehand informed VentureBeat that it designed the Olmo 3 household of fashions to supply enterprises and analysis labs extra management and understanding of the information and coaching that went into the mannequin.
Organizations may add to the mannequin’s information combine and retrain it to additionally study from what’s been added.
This has lengthy been a dedication for Ai2, which additionally affords a software referred to as OlmoTrace that tracks how LLM outputs match its coaching information.
“Together, Olmo 3.1 Think 32B and Olmo 3.1 Instruct 32B show that openness and performance can advance together. By extending the same model flow, we continue to improve capabilities while retaining end-to-end transparency over data, code, and training decisions,” Ai2 mentioned.
