As it turns out, letting a RL training run continue will make models better (an extra 3.5 weeks for this one)! 3.1 is an improvement on all metrics over its predecessors. The paper is also updated and dives even deeper into all the details.
Specs
Params32B
LicenseApache-2.0
Tags
modelsmodels/llmsmodels/llms/reasoningartifacts/17
Capability · Artificial Analysis
AA Index
8.1
Frontier lag
21.2 mo
claude-3-opus
04 Mar 2024
RAM score
—
Hugging Face Downloads
6.3K
last 30d
50.1K
all time
HF Likes
109
Relative Adoption Metric contextualizes downloads against the model's size bucket.
VAIL Fingerprint
0130:0161:020a:0304:04e8:08a9:1280:5394
Explore other models with behavioral similarity to Olmo-3.1-32B-Think.
Related Models
