DM-JEPA 1.1
DM-JEPA 1.1 by Danger Labs is a decision model: it answers typed questions with a probability for each allowed answer instead of generating text. It scores 4.0 on the Jev Decision Index (rank 152).
Pricing
No hosted price is listed. The weights are open: the cost is your own compute.
Specifications
- Provider
- Danger Labs
- Parameters
- 149M
- Released
- Oct 2026
- Open weights
- Yes
- Question types
- Choice (one of N options), Score (ordered rubric), Yes / no
- Mechanism
- Encoder classifier
- Backbone
- answerdotai/ModernBERT-base
- Jev-compatible request
- No
- Runs on CPU
- Yes
- License
- mit
- Hugging Face
- DangerLabs/DM-JEPA
Benchmarks
- Jev Decision IndexECE 0.445
- 4.0
Jev Decision Index: public 19.2, ECE 0.445, Brier 0.936. Lower ECE means its probabilities can be taken at face value.
Self-reported by the publisher
The model's own claims, often on its own sets or a self-run copy of a public suite. Not independently verified and never ranked alongside measured results.
- jev-decision-index-0.3-sampleSelf-reported
- 65.7
Speed & latency
Compare DM-JEPA 1.1 with…
FAQ
How much does DM-JEPA 1.1 cost?
DM-JEPA 1.1 has no hosted price listed; its weights are open, so the cost is the compute you run it on.
What questions can DM-JEPA 1.1 answer?
DM-JEPA 1.1 answers choice (one of n options), score (ordered rubric), yes / no questions, returning a probability for each allowed answer.
Is DM-JEPA 1.1 well calibrated?
On the Jev Decision Index its expected calibration error (ECE) is 0.445; below about 0.05, a stated 80% confidence is right roughly 80% of the time.
Is DM-JEPA 1.1 open weight, and can it run on a CPU?
Yes, DM-JEPA 1.1 has open weights. It is small enough to run on a CPU.
Data as of 2026-10-14. Source: Metatext decision-model catalogue, 2026-10-14 (Jev Decision Index, Hugging Face). Pricing is per 1M tokens (USD); confirm with the provider before production use.