Olmo 3 32B
Allen Institute for AI ·
Verified
2 of 2 published values traced to a source3 primary sources, 3 archived1 not disclosed by the lab
Why this status
Every value this record asserts — release date and parameter count — was found in an archived primary source. Context window is not recorded: none of the cited sources states one, so nothing is claimed about it. Capabilities evidenced from the primary sources: coding: “On math benchmarks, Olmo 3-Think (7B) matches Qwen 3 8B on MATH and comes within a few points on AIME 2024 and 2025, and also leads all comparison models on HumanEvalPlus” | function_calling: “Olmo 3 model construction targets long-context reasoning, function calling, coding, instruction following, general chat, and knowledge recall.”.
What these states mean · How records are judged · Has this record changed?
Part of Ai2's fully-open Olmo 3 family, released with every checkpoint, data point and dependency used to build it.
Details
| Released | November 20, 2025stated in allenai.org, huggingface.coOlmo 3 32B was released on November 20, 2025.
|
|---|---|
| Company | Allen Institute for AI |
| Family | Olmo |
| Released alongside | Olmo 3 7B |
| Era | Reasoning models |
| Type | Language model · LLM |
| Modalities | Text → Text |
| Capabilities | Coding, Function calling |
| Weights | Open weights |
| Licence | Apache-2.0 |
| Context window | Not disclosed |
| Parameters | 32Bstated in allenai.org, arxiv.org, huggingface.coOlmo 3 32B has 32,000,000,000 parameters.
|
Current information, elsewhere
This record is a historical one: every figure above is traced to a dated primary source. For what is true today — live pricing, current rankings, availability — these are better maintained than anything here could be.
- Current price and providers OpenRouter ↗
- Current benchmark scores Artificial Analysis ↗
- Weights and model card Hugging Face ↗
Sources
Record status: verified · confidence 90/100 · 3 of 3 primary
Every value this record asserts — release date and parameter count — was found in an archived primary source. Context window is not recorded: none of the cited sources states one, so nothing is claimed about it. Capabilities evidenced from the primary sources: coding: “On math benchmarks, Olmo 3-Think (7B) matches Qwen 3 8B on MATH and comes within a few points on AIME 2024 and 2025, and also leads all comparison models on HumanEvalPlus” | function_calling: “Olmo 3 model construction targets long-context reasoning, function calling, coding, instruction following, general chat, and knowledge recall.”.
- allenai.org Official announcement archived
- arxiv.org Technical paper archived
- huggingface.co Model card archived
Primary means published by the organisation that made the model. Verified records require at least one.
Olmo family
- Olmo 3 7B November 20, 2025
- Olmo 3 32B November 20, 2025
Compare Olmo 3 32B with another model →
See Olmo 3 32B on the interactive timeline →