Respan's behaviour-scoring model for evals, guardrails and monitoring. For each plain-language behaviour you define, it reads a conversation or agent trace and returns the probability the behaviour is present, absent or not observable, in one forward pass.
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.
Decides
noul, classify
choice, score, noul
Architecture
span
this-that
Fine-tuned from
—
mapika/decider
License
proprietary
mit
Availability
Hosted API
Open weights
Hosted by
Respan
—
Input price
$0.020/MTok
—
Decision accuracy
—
87.8%
Calibration error
—
—
Valid action rate
—
—
Median latency
—
31.4 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 span-01 and this-that-model?
span-01 is from Respan and this-that-model from FLock.io. span-01 is only available as a hosted API; this-that-model has open weights you can download and run. Both answer noul questions. Only span-01 answers classify. Only this-that-model answers choice and score. span-01 is licensed proprietary; this-that-model, mit.
Which is more accurate, span-01 or this-that-model?
Only this-that-model publishes an accuracy figure (87.8% on limberc/this-that-complex-decisions (1,710 questions, FLock's benchmark)); span-01 does not, so there is no comparison to make without your own test.
Which is cheaper, span-01 or this-that-model?
span-01: $0.02 / $0 per 1M. this-that-model: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run span-01 or this-that-model locally?
this-that-model yes — systemone pull flock-io/this-that-model downloads its weights. The other is only served as a hosted API.
