bobcat-1.3
bobcat-1.3 by sanghwa-na is a decision model: it answers typed questions with a probability for each allowed answer instead of generating text. It scores 64.8 on the Jev Decision Index (rank 22).
Pricing
No hosted price is listed. The weights are open: the cost is your own compute.
Specifications
- Provider
- sanghwa-na
- Parameters
- 31B
- 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
- google/gemma-4-31B-it
- Jev-compatible request
- Yes
- Runs on CPU
- No
- License
- apache-2.0
- Hugging Face
- sanghwa-na/bobcat-1.3
Benchmarks
- Jev Decision IndexECE 0.102
- 64.8
Jev Decision Index: public 59.3, ECE 0.102, Brier 0.386. 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
- 59.3
Speed & latency
Compare bobcat-1.3 with…
FAQ
How much does bobcat-1.3 cost?
bobcat-1.3 has no hosted price listed; its weights are open, so the cost is the compute you run it on.
What questions can bobcat-1.3 answer?
bobcat-1.3 answers choice (one of n options), score (ordered rubric), yes / no questions, returning a probability for each allowed answer.
Is bobcat-1.3 well calibrated?
On the Jev Decision Index its expected calibration error (ECE) is 0.102; below about 0.05, a stated 80% confidence is right roughly 80% of the time.
Is bobcat-1.3 open weight, and can it run on a CPU?
Yes, bobcat-1.3 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.