Skip to content

Solomon v1.1

Doccy HealthDecision modelOpen weights

Solomon v1.1 by Doccy Health is a decision model: it answers typed questions with a probability for each allowed answer instead of generating text. It scores 40.9 on the Jev Decision Index (rank 79).

Pricing

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

Specifications

Provider
Doccy Health
Parameters
28B
Released
Sep 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/Qwen3.8-27B
Jev-compatible request
No
Runs on CPU
No
License
apache-2.0
Hugging Face
DoccyHealth/Solomon

Benchmarks

Jev Decision IndexECE 0.081
40.9

Jev Decision Index: public 38.1, ECE 0.081, Brier 0.442. Lower ECE means its probabilities can be taken at face value.

Speed & latency

Median latency per call (Decision Index)
224 ms

Compare Solomon v1.1 with…

FAQ

How much does Solomon v1.1 cost?

Solomon v1.1 has no hosted price listed; its weights are open, so the cost is the compute you run it on.

What questions can Solomon v1.1 answer?

Solomon v1.1 answers choice (one of n options), score (ordered rubric), yes / no questions, returning a probability for each allowed answer.

Is Solomon v1.1 well calibrated?

On the Jev Decision Index its expected calibration error (ECE) is 0.081; below about 0.05, a stated 80% confidence is right roughly 80% of the time.

Is Solomon v1.1 open weight, and can it run on a CPU?

Yes, Solomon v1.1 has open weights. It needs a GPU to run at useful speed.

Data as of 2026-10-14. Source: Metatext decision-model catalogue, 2026-10-14 (Jev Decision Index, Enterprise Decision Arena, Hugging Face). Pricing is per 1M tokens (USD); confirm with the provider before production use.