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.
FLock.io's typed-decision model, fine-tuned from Mapika's decider-2b. Reads one hidden state per question and scores the declared options, so an answer outside the list cannot occur; several questions about one state share a forward pass.
Decides
choice, score, noul, classify, route
choice, score, noul
Architecture
metask-jev
this-that
Fine-tuned from
qwen/qwen3.5-4b
mapika/decider
License
apache-2.0
mit
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
80.1%
87.8%
Calibration error
—
—
Valid action rate
—
—
Median latency
62.8 ms
31.4 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 metask-jev and this-that-model?
metask-jev is from Metask Lab and this-that-model from FLock.io. Both have open weights you can download and run. Both answer choice, score and noul questions. Only metask-jev answers classify and route. this-that-model is the smaller model, at 1.9B parameters to 4.5B. metask-jev is licensed apache-2.0; this-that-model, mit.
Which is more accurate, metask-jev or this-that-model?
They report on different suites — metask-jev 80.1% on JevBench v1.2 public set (231 items) at 4,096 tokens, maker's run, this-that-model 87.8% on limberc/this-that-complex-decisions (1,710 questions, FLock's benchmark) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, metask-jev or this-that-model?
metask-jev: Free (open weights). this-that-model: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, metask-jev or this-that-model?
By their publishers’ figures, this-that-model answers in about 31.4 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 this-that-model locally?
Yes, both: systemone pull metask-lab/metask-jev and systemone pull flock-io/this-that-model download the weights.
Evaluation suite
JevBench v1.2 public set (231 items) at 4,096 tokens, maker's run
