JEV-35B
JEV-35B by AutoTrust AI Lab is a decision model: it answers typed questions with a probability for each allowed answer instead of generating text. It scores 57.6 on the Jev Decision Index (rank 57).
Pricing
No hosted price is listed. The weights are open: the cost is your own compute.
Specifications
- Provider
- AutoTrust AI Lab
- Parameters
- 36B
- 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/Qwen3.5-35B-A3B
- Jev-compatible request
- Yes
- Runs on CPU
- No
- License
- apache-2.0
- Hugging Face
- autotrust/JEV-35B
Benchmarks
- Jev Decision IndexECE 0.085
- 57.6
Jev Decision Index: public 59.7, ECE 0.085, Brier 0.359. 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
- 59.7
- Decision Index 0.3 public suiteSelf-reported
- 59.7
Speed & latency
Compare JEV-35B with…
FAQ
How much does JEV-35B cost?
JEV-35B has no hosted price listed; its weights are open, so the cost is the compute you run it on.
What questions can JEV-35B answer?
JEV-35B answers choice (one of n options), score (ordered rubric), yes / no questions, returning a probability for each allowed answer.
Is JEV-35B well calibrated?
On the Jev Decision Index its expected calibration error (ECE) is 0.085; below about 0.05, a stated 80% confidence is right roughly 80% of the time.
Is JEV-35B open weight, and can it run on a CPU?
Yes, JEV-35B has open weights. It needs a GPU to run at useful speed.
Data as of 2026-10-26. Source: Metatext decision-model catalogue, 2026-10-14 (Hugging Face). Pricing is per 1M tokens (USD); confirm with the provider before production use.