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.
Together AI's Jev-style classifier. A LoRA fine-tune of Qwen3.5-4B that reads a state, a question and 2 to 24 options and returns one option letter. Served on Together's platform; recipe published.
Decides
choice, score, noul, classify, route
choice, classify, route
Architecture
metask-jev
tev
Fine-tuned from
qwen/qwen3.5-4b
qwen/qwen3.5-4b
License
apache-2.0
Unspecified — weights licence being finalised
Availability
Open weights
Open weights + hosted API
Hosted by
—
Together AI
Input price
—
$0.042/MTok
Decision accuracy
80.1%
88.0%
Calibration error
—
—
Valid action rate
—
—
Median latency
62.8 ms
—
p95 latency
—
—
Evaluation suite
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 tev1?
metask-jev is from Metask Lab and tev1 from Together AI. metask-jev has open weights you can download and run; tev1 has open weights and a hosted API. Both answer choice, classify and route questions. Only metask-jev answers score and noul. tev1 is the smaller model, at 4.0B parameters to 4.5B. metask-jev is licensed apache-2.0; tev1, other.
Which is more accurate, metask-jev or tev1?
They report on different suites — metask-jev 80.1% on JevBench v1.2 public set (231 items) at 4,096 tokens, maker's run, tev1 88.0% on Together development set (reused, not held out) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, metask-jev or tev1?
metask-jev: Free (open weights). tev1: $0.042 / $0 per 1M, or free to self-host. Open weights cost nothing per call beyond your own hardware.
Can I run metask-jev or tev1 locally?
Yes, both: systemone pull metask-lab/metask-jev and systemone pull together-ai/tev1 download the weights.
JevBench v1.2 public set (231 items) at 4,096 tokens, maker's run
