HEAD TO HEAD

decider vs jevk5

Q: Can I run decider or jevk5 locally?

Yes, both: systemone pull mapika/decider and systemone pull alibi-serikbay/jevk5 download the weights.

Mapika: decider and Alibi Serikbay: jevk5, compared on what they decide, where they run, what they cost and what their publishers report.

The short version

Both have open weights you can download and run.
Both answer choice, score, noul, classify and route questions.
decider is the smaller model, at 2.0B parameters to 4.0B.

Property	mapika/decider	alibi-serikbay/jevk5
Summary	The most-downloaded open System One reproduction. Merged Qwen3.5 fine-tunes, trained on about 95 public decision sets, then calibration-aware RL and a rank-64 LoRA, that softmax letter logits at an answer slot.	Qwen3.5-4B with a merged rank-16 LoRA distilled from 17,408 teacher questions and 30,000 public training rows, read out as a temperature-scaled softmax over answer-letter logits. Also in 9B, 2B and GGUF.
Decides	choice, score, noul, classify, route	choice, score, noul, classify, route
Architecture	decider	jevk5
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	80.2%	78.4%
Calibration error	0.038	0.035
Valid action rate	—	—
Median latency	3.2 ms	13.2 ms
p95 latency	—	—
Evaluation suite	Decider 67-task regression set	JevBench public hard tier

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 jevk5?

decider is from Mapika and jevk5 from Alibi Serikbay. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. decider is the smaller model, at 2.0B parameters to 4.0B.

Which is more accurate, decider or jevk5?

They report on different suites — decider 80.2% on Decider 67-task regression set, jevk5 78.4% on JevBench public hard tier — so the numbers do not rank them. Test both on your own labelled examples.

Which is cheaper, decider or jevk5?

decider: Free (open weights). jevk5: Free (open weights). Open weights cost nothing per call beyond your own hardware.

Which is faster, decider or jevk5?

By their publishers’ figures, decider answers in about 3.2 ms at the median and jevk5 in about 13.2 ms — measured on different hardware, so treat it as a rough guide.

Can I run decider or jevk5 locally?

Yes, both: systemone pull mapika/decider and systemone pull alibi-serikbay/jevk5 download the weights.

mapika/decider

alibi-serikbay/jevk5

Summary

The most-downloaded open System One reproduction. Merged Qwen3.5 fine-tunes, trained on about 95 public decision sets, then calibration-aware RL and a rank-64 LoRA, that softmax letter logits at an answer slot.

Qwen3.5-4B with a merged rank-16 LoRA distilled from 17,408 teacher questions and 30,000 public training rows, read out as a temperature-scaled softmax over answer-letter logits. Also in 9B, 2B and GGUF.

Decides

choice, score, noul, classify, route

Architecture

decider

jevk5

Fine-tuned from

qwen/qwen3.5-2b-base

qwen/qwen3.5-4b

License

apache-2.0

Availability

Open weights

Hosted by

—

Input price

—

Decision accuracy

80.2%

78.4%

Calibration error

0.038

0.035

Valid action rate

—

Median latency

3.2 ms

13.2 ms

p95 latency

—

Evaluation suite

Decider 67-task regression set

JevBench public hard tier