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.
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
decider
tev
Fine-tuned from
qwen/qwen3.5-2b-base
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
80.2%
88.0%
Calibration error
0.038
—
Valid action rate
—
—
Median latency
3.2 ms
—
p95 latency
—
—
Evaluation suite
Decider 67-task regression set
Together development set (reused, not held out)
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 tev1?
decider is from Mapika and tev1 from Together AI. decider has open weights you can download and run; tev1 has open weights and a hosted API. Both answer choice, classify and route questions. Only decider answers score and noul. decider is the smaller model, at 2.0B parameters to 4.0B. decider is licensed apache-2.0; tev1, other.
Which is more accurate, decider or tev1?
They report on different suites — decider 80.2% on Decider 67-task regression set, 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, decider or tev1?
decider: 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 decider or tev1 locally?
Yes, both: systemone pull mapika/decider and systemone pull together-ai/tev1 download the weights.
