A family of open System One models by Mark Marosi, decider-0.8b, decider-2b, decider-4b and decider-35b-a3b on Qwen3.5 bases, that softmax letter logits at an answer slot. This page carries decider-2b v11.
Metask Lab's calibrated decision model in 16 languages. Qwen3.5-4B with a merged LoRA trained with the Nimble candidate-logit objective; one forward pass and a softmax over at most 26 answer-letter logits, with one temperature per question type.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
decider
metask-jev
Fine-tuned from
qwen/qwen3.5-2b-base
qwen/qwen3.5-4b
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
75.2%
80.1%
Calibration error
—
—
Valid action rate
—
—
Median latency
—
62.8 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 decider and metask-jev?
decider is from Mapika and metask-jev from Metask Lab. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. decider reads up to 32K tokens of state, against 4K tokens for metask-jev. decider is the smaller model, at 1.9B parameters to 4.5B.
Which is more accurate, decider or metask-jev?
They report on different suites — decider 75.2% on Decider regression set, 28 held-out tasks (decider-2b v11), metask-jev 80.1% on JevBench v1.2 public set (231 items) at 4,096 tokens, maker's run — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, decider or metask-jev?
decider: Free (open weights). metask-jev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run decider or metask-jev locally?
Yes, both: systemone pull mapika/decider and systemone pull metask-lab/metask-jev download the weights.
