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.
A Situated World Model for fast judgment in agent loops.
Decides
choice, score, noul, classify, route
choice, route, classify
Architecture
metask-jev
trio-spark
Fine-tuned from
qwen/qwen3.5-4b
—
License
apache-2.0
proprietary
Availability
Open weights
Hosted API
Hosted by
—
MachineFi
Input price
—
$0.042/MTok
Decision accuracy
80.1%
—
Calibration error
—
—
Valid action rate
—
—
Median latency
62.8 ms
—
p95 latency
—
—
Evaluation suite
JevBench v1.2 public set (231 items) at 4,096 tokens, maker's run
—
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 trio-spark-v1?
metask-jev is from Metask Lab and trio-spark-v1 from MachineFi. metask-jev has open weights you can download and run; trio-spark-v1 is only available as a hosted API. Both answer choice, classify and route questions. Only metask-jev answers score and noul. metask-jev reads up to 4K tokens of state, against 1K tokens for trio-spark-v1. metask-jev is licensed apache-2.0; trio-spark-v1, proprietary.
Which is more accurate, metask-jev or trio-spark-v1?
Only metask-jev publishes an accuracy figure (80.1% on JevBench v1.2 public set (231 items) at 4,096 tokens, maker's run); trio-spark-v1 does not, so there is no comparison to make without your own test.
Which is cheaper, metask-jev or trio-spark-v1?
metask-jev: Free (open weights). trio-spark-v1: $0.042 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run metask-jev or trio-spark-v1 locally?
metask-jev yes — systemone pull metask-lab/metask-jev downloads its weights. The other is only served as a hosted API.
