The most-downloaded open System One reproduction. Merged Qwen3.5 fine-tunes, trained on about 95 public decision sets, then calibration-aware RL and a rank-64 LoRA, that softmax letter logits at an answer slot.
The flagship of the vLLM Semantic Router team's Decision 1.0 family. Qwen3.5-9B with a shared candidate head returns a probability for every supplied answer to choice, yes/no and score questions, over a 16,384-token input.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
decider
decision
Fine-tuned from
qwen/qwen3.5-2b-base
qwen/qwen3.5-9b
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
80.2%
77.4%
Calibration error
0.038
—
Valid action rate
—
—
Median latency
3.2 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 decider and decision?
decider is from Mapika and decision from vLLM Semantic Router. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. decider is the smaller model, at 2.0B parameters to 9.0B.
Which is more accurate, decider or decision?
They report on different suites — decider 80.2% on Decider 67-task regression set, decision 77.4% on vLLM-SR decision benchmark (54 tasks, 3,766 decisions, weighted) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, decider or decision?
decider: Free (open weights). decision: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run decider or decision locally?
Yes, both: systemone pull mapika/decider and systemone pull vllm-semantic-router/decision download the weights.
