Dinah-0
Dinah-0 by Lukitaduarte is a decision model: it answers typed questions with a probability for each allowed answer instead of generating text. It scores 13.9 on the Jev Decision Index (rank 132).
Pricing
No hosted price is listed. The weights are open: the cost is your own compute.
Specifications
- Provider
- Lukitaduarte
- Parameters
- 150M
- Released
- Sep 2026
- Open weights
- Yes
- Question types
- Choice (one of N options), Score (ordered rubric), Yes / no
- Mechanism
- Encoder classifier
- Backbone
- Tropic-AI/moBERTo
- Jev-compatible request
- Yes
- Runs on CPU
- Yes
- License
- cc-by-nc-4.0
- Hugging Face
- Lukitaduarte/dinah-0
Benchmarks
- Jev Decision IndexECE 0.104
- 13.9
Jev Decision Index: public 26.1, ECE 0.104, Brier 0.578. 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 public suite (self-run)Self-reportedDecision Index public balanced skill, edition 0.2.1 kit (release-v2.1), self-run
- 27.6
Speed & latency
Compare Dinah-0 with…
FAQ
How much does Dinah-0 cost?
Dinah-0 has no hosted price listed; its weights are open, so the cost is the compute you run it on.
What questions can Dinah-0 answer?
Dinah-0 answers choice (one of n options), score (ordered rubric), yes / no questions, returning a probability for each allowed answer.
Is Dinah-0 well calibrated?
On the Jev Decision Index its expected calibration error (ECE) is 0.104; below about 0.05, a stated 80% confidence is right roughly 80% of the time.
Is Dinah-0 open weight, and can it run on a CPU?
Yes, Dinah-0 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.