FLock.io's typed-decision model, fine-tuned from Mapika's decider-2b. Reads one hidden state per question and scores the declared options, so an answer outside the list cannot occur; several questions about one state share a forward pass.
A Gemma 4 12B fine-tune for typed decisions that also chats and reads images. Ships as GGUF for llama.cpp, holds a 64K context on a 16 GB GPU, and serves /v1/systemone next to /v1/chat/completions.
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 this-that-model and winnow?
this-that-model is from FLock.io and winnow from EldanRing. Both have open weights you can download and run. Both answer choice, score and noul questions. Only winnow answers classify and route. this-that-model is the smaller model, at 1.9B parameters to 12B. this-that-model is licensed mit; winnow, apache-2.0.
Which is more accurate, this-that-model or winnow?
They report on different suites — this-that-model 87.8% on limberc/this-that-complex-decisions (1,710 questions, FLock's benchmark), winnow 85.7% on JevBench public subset (231 items), Q8_0 — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, this-that-model or winnow?
this-that-model: Free (open weights). winnow: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, this-that-model or winnow?
By their publishers’ figures, this-that-model answers in about 31.4 ms at the median and winnow in about 143 ms — measured on different hardware, so treat it as a rough guide.
Can I run this-that-model or winnow locally?
Yes, both: systemone pull flock-io/this-that-model and systemone pull eldanring/winnow download the weights.
