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.
Small open typed-decision model with calibrated probabilities, first-class Nepali coverage.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
metask-jev
mira
Fine-tuned from
qwen/qwen3.5-4b
jhu-clsp/mmbert-small
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
80.1%
74.5%
Calibration error
—
0.025
Valid action rate
—
100.0%
Median latency
62.8 ms
30 ms
p95 latency
—
43 ms
Evaluation suite
JevBench v1.2 public set (231 items) at 4,096 tokens, maker's run
s1-decision-bench
Latest version
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 metask-jev and mira?
metask-jev is from Metask Lab and mira from SAGEA. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions.
Which is more accurate, metask-jev or mira?
They report on different suites — metask-jev 80.1% on JevBench v1.2 public set (231 items) at 4,096 tokens, maker's run, mira 74.5% on s1-decision-bench — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, metask-jev or mira?
metask-jev: Free (open weights). mira: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, metask-jev or mira?
By their publishers’ figures, mira answers in about 30 ms at the median and metask-jev in about 62.8 ms — measured on different hardware, so treat it as a rough guide.
Can I run metask-jev or mira locally?
Yes, both: systemone pull metask-lab/metask-jev and systemone pull sagea/mira download the weights.
