All models

COMPARE

2 models, side by side.

What each one decides, how well calibrated it is, how fast it answers and what it costs to pull. Up to 4 at a time; the better value in each row is marked.

Propertyalibi-serikbay/jevk5wfzyx/von
SummaryQwen3.5-4B with a merged rank-16 LoRA distilled from 17,408 teacher questions and 30,000 public training rows, read out as a temperature-scaled softmax over answer-letter logits. Also in 9B, 2B and GGUF.A ModernBERT-large encoder with an option-marker head. Premise and options are packed into one sequence and each option's marker is scored in a single bidirectional pass; version 1.2 makes the scoring order-invariant.
Decideschoice, score, noul, classify, routechoice, score, noul, classify
Architecturejevk5von
Fine-tuned fromqwen/qwen3.5-4banswerdotai/modernbert-large
Licenseapache-2.0apache-2.0
AvailabilityOpen weightsOpen weights
Hosted by——
Input price——
Decision accuracy78.4%63.9%
Calibration error0.0350.045
Valid action rate——
Median latency13.2 ms18 ms
p95 latency——
Evaluation suiteJevBench public hard tierJevBench public standard tier
Latest version0.3.01.2.0
VariantsSHA256SUMS—
Size of latest version7.9 GB2.9 GB
Files82
Downloads00
Stars00
Tagssystem-one, qwen, lora, distilled, 4bsystem-one, encoder, modernbert, 395m
UpdatedSep 25, 2026Sep 25, 2026