Matilda Jev v1.5
Matilda Jev v1.5 by Maincode is a decision model: it answers typed questions with a probability for each allowed answer instead of generating text. It scores 59.2 on the Jev Decision Index (rank 11).
Pricing
No hosted price is listed. The weights are open: the cost is your own compute.
Specifications
- Provider
- Maincode
- Parameters
- 26B
- 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/Qwen3.8-27B
- Jev-compatible request
- Yes
- Runs on CPU
- No
- License
- apache-2.0
- Hugging Face
- Maincode/matilda-jev-v1.5
Benchmarks
- Jev Decision IndexECE 0.077
- 59.2
- Jev Decision Index — VisionECE 0.071
- 62.0
Jev Decision Index: public 63.5, ECE 0.077, Brier 0.337. 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
- 63.5
Speed & latency
Compare Matilda Jev v1.5 with…
FAQ
How much does Matilda Jev v1.5 cost?
Matilda Jev v1.5 has no hosted price listed; its weights are open, so the cost is the compute you run it on.
What questions can Matilda Jev v1.5 answer?
Matilda Jev v1.5 answers choice (one of n options), score (ordered rubric), yes / no questions, returning a probability for each allowed answer.
Is Matilda Jev v1.5 well calibrated?
On the Jev Decision Index its expected calibration error (ECE) is 0.077; below about 0.05, a stated 80% confidence is right roughly 80% of the time.
Is Matilda Jev v1.5 open weight, and can it run on a CPU?
Yes, Matilda Jev v1.5 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, Hugging Face). Pricing is per 1M tokens (USD); confirm with the provider before production use.