Skip to content

Saina Helm 2.0

SainaDecision modelOpen weights

Saina Helm 2.0 by Saina is a decision model: it answers typed questions with a probability for each allowed answer instead of generating text. It scores 20.8 on the Jev Decision Index (rank 122).

Pricing

No hosted price is listed. The weights are open: the cost is your own compute.

Specifications

Provider
Saina
Parameters
853M
Released
Oct 2026
Open weights
Yes
Question types
Choice (one of N options), Score (ordered rubric), Yes / no
Mechanism
Decoder LM with a decision readout
Backbone
Qwen/Qwen3.5-0.8B
Jev-compatible request
No
Runs on CPU
Yes
License
apache-2.0
Hugging Face
run-saina/saina-helm-2-0.8b

Benchmarks

Jev Decision IndexECE 0.247
20.8

Jev Decision Index: public 30.2, ECE 0.247, Brier 0.669. 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 0.3 kit (release-v3), self-run
28.4

Speed & latency

Median latency per call (Decision Index)
39 ms

Compare Saina Helm 2.0 with…

FAQ

How much does Saina Helm 2.0 cost?

Saina Helm 2.0 has no hosted price listed; its weights are open, so the cost is the compute you run it on.

What questions can Saina Helm 2.0 answer?

Saina Helm 2.0 answers choice (one of n options), score (ordered rubric), yes / no questions, returning a probability for each allowed answer.

Is Saina Helm 2.0 well calibrated?

On the Jev Decision Index its expected calibration error (ECE) is 0.247; below about 0.05, a stated 80% confidence is right roughly 80% of the time.

Is Saina Helm 2.0 open weight, and can it run on a CPU?

Yes, Saina Helm 2.0 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.