A 0.4B decision model made from the first 20 layers of Qwen3-0.6B plus a small attention head that compares options. It answers choice, noul and score questions in one pass, and choice order cannot change its answer by construction. Non-commercial licence.
An independent Jev-shaped reproduction on DeBERTa-v3-large. One state and any number of choice, score and yes/no questions go in, and a calibrated distribution per question comes out of one forward pass. Public gold labels only.
Decides
choice, score, noul
choice, score, noul, classify
Architecture
bev-decider
open-jev
Fine-tuned from
qwen/qwen3-0.6b
microsoft/deberta-v3-large
License
cc-by-nc-4.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
74.7%
85.4%
Calibration error
—
0.022
Valid action rate
—
—
Median latency
—
28 ms
p95 latency
—
—
Figures are from each model’s manifest; accuracy and latency are what the publishers report, on their own suites and hardware. Add a third model.
Questions
What is the difference between bev-decider and open-jev-deberta-v3-large?
bev-decider is from Avishek Biswas and open-jev-deberta-v3-large from Kotoba Labs. Both have open weights you can download and run. Both answer choice, score and noul questions. Only open-jev-deberta-v3-large answers classify. bev-decider reads up to 2K tokens of state, against 512 tokens for open-jev-deberta-v3-large. open-jev-deberta-v3-large is the smaller model, at 434M parameters to 478M. bev-decider is licensed cc-by-nc-4.0; open-jev-deberta-v3-large, apache-2.0.
Which is more accurate, bev-decider or open-jev-deberta-v3-large?
They report on different suites — bev-decider 74.7% on avbiswas/bev-decision test split (5,000 held-out questions over 2,617 states), the maker's own, open-jev-deberta-v3-large 85.4% on Kotoba held-out test, seen question types (banking77, SST-5, BoolQ) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, bev-decider or open-jev-deberta-v3-large?
bev-decider: Free (open weights). open-jev-deberta-v3-large: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run bev-decider or open-jev-deberta-v3-large locally?
Yes, both: systemone pull avishek-biswas/bev-decider and systemone pull kotoba-labs/open-jev-deberta-v3-large download the weights.
Evaluation suite
avbiswas/bev-decision test split (5,000 held-out questions over 2,617 states), the maker's own
Kotoba held-out test, seen question types (banking77, SST-5, BoolQ)
