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.
Invergent's decision model for text and images. A fine-tune of Gemma-4-26B-A4B (about 4B parameters active per token) that answers Choice, Noul and Score questions, with an optional thinking mode for harder questions.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
metask-jev
rune
Fine-tuned from
qwen/qwen3.5-4b
google/gemma-4-26b-a4b-it
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights + hosted API
Hosted by
—
Invergent
Input price
—
—
Decision accuracy
80.1%
—
Calibration error
—
—
Valid action rate
—
—
Median latency
62.8 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 rune?
metask-jev is from Metask Lab and rune from Surogate (Invergent). metask-jev has open weights you can download and run; rune has open weights and a hosted API. Both answer choice, score, noul, classify and route questions. rune reads up to 262K tokens of state, against 4K tokens for metask-jev. metask-jev is the smaller model, at 4.5B parameters to 26B.
Which is more accurate, metask-jev or rune?
Only metask-jev publishes an accuracy figure (80.1% on JevBench v1.2 public set (231 items) at 4,096 tokens, maker's run); rune does not, so there is no comparison to make without your own test.
Which is cheaper, metask-jev or rune?
metask-jev: Free (open weights). rune: Hosted, price not published, or free to self-host. Open weights cost nothing per call beyond your own hardware.
Can I run metask-jev or rune locally?
Yes, both: systemone pull metask-lab/metask-jev and systemone pull surogate/rune download the weights.
Evaluation suite
JevBench v1.2 public set (231 items) at 4,096 tokens, maker's run
