LANGUAGE MODEL Allen AI Last updated:

OLMo 2

Allen AI's Fully Open Foundation

The Allen Institute's truly-open language model — not just weights, but the training data (Dolma), the training code, intermediate checkpoints, and evaluation suites. OLMo 2 (and the instruction- tuned Tulu 3 family) is what most academic ML researchers use when they need a model they can REPRODUCE, not just download.

Try demo
Cost
Free
Open weights — self-host
Context
4K
Up to 4,096 tokens
How are Intelligence, Speed & Cost bucketed?
Intelligence and Speed buckets are percentile ranks on Artificial Analysis. Cost buckets are fixed dollar thresholds keyed off output-token price ($/M out).
Intelligence
  • Top 1%≤ 1%
  • Top 5%≤ 5%
  • Top 10%≤ 10%
  • Good≤ 25%
  • Medium≤ 50%
  • Below avg> 50%
Speed
  • Top 1%≥ 345 tok/s
  • Top 5%≥ 237 tok/s
  • Top 10%≥ 196 tok/s
  • Good≥ 146 tok/s
  • Medium≥ 90 tok/s
  • Slow< 90 tok/s
Cost
  • Freeopen weights · self-host
  • Low< $1 / M out
  • Moderate$1–5 / M out
  • High≥ $5 / M out

Why it matters

Pushes the definition of "open source AI" — exposes how partial Llama, Mistral, and Qwen open releases really are. Ai2's continued pressure (Tulu 3 405B, Molmo, OLMoE) anchors the open-science end of the model spectrum.

Core Capabilities

Long Documents
Handles entire codebases, books, and multi-doc RAG.
Generative
Produces images, video, audio, or other media.
Research
Foundational paper or scientific contribution.

Context Window

4k tokens
≈ short doc
4k This model 本模型
32k Long docs 长文档
128k Books 整本书
400k Multi-doc 多文档
1M Codebase 整个代码库
10M

Availability

API
Not available
Product / App
Not available
Open Source
Released
Enterprise

Pricing Model

Free / self-host
Open weights — pay only for compute.
Self-host

Capability / Performance

Where this model sits relative to the middle 60% of models in the tree. All scores are 0–10 (higher is better).

Lower 20% Upper 80% This model
Reasoning
AA Intelligence Index · scaled to 10
1.7
5.6
1.5
Coding
SciCode · scaled to 10
1.8
4.3
0.8
Agentic tasks
Terminal-Bench Hard · scaled to 10
0.2
3.6
0.0
Context / memory
Context window size · log-scaled
6.0
9.0
1.0
Lower 20% 20th percentile — 20% of models score below this This model Where the current model lands Upper 80% 80th percentile — only 20% of models score above this Percentile boundaries are computed across every model in the tree that reports the underlying benchmark for each capability.

What it feels like

  • Language model from Allen AI — see the linked sources below for benchmark and review coverage

Best use cases

  • General-purpose tasks within Allen AI's deployment footprint
  • See the model spec and sources block for benchmarked use cases

Tools to try

Not ideal for

  • Tasks far outside the modalities listed in this model's spec
  • Workflows where a more recent successor in the same family scores higher

Model Evolution

View full evolution tree →

Allen Institute for AI