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.
Juspay's open decision model. Qwen3.6-35B-A3B with a merged rank-16 LoRA, shipped with a pinned SGLang serving bundle that answers Choice, Score and Noul questions over text, images or a video through a TypeSafe-compatible /v1/systemone API.
Decides
noul, classify
choice, score, noul, classify, route
Architecture
span
xor
Fine-tuned from
—
qwen/qwen3.6-35b-a3b
License
proprietary
apache-2.0
Availability
Hosted API
Open weights
Hosted by
Respan
—
Input price
$0.020/MTok
—
Decision accuracy
—
90.0%
Calibration error
—
0.073
Valid action rate
—
—
Median latency
—
69 ms
p95 latency
—
162 ms
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 xor?
span-01 is from Respan and xor from Juspay. span-01 is only available as a hosted API; xor has open weights you can download and run. Both answer noul and classify questions. Only xor answers choice, score and route. span-01 is licensed proprietary; xor, apache-2.0.
Which is more accurate, span-01 or xor?
Only xor publishes an accuracy figure (90.0% on JevBench public set (231 items), maker's self-run of Xor 1.2); span-01 does not, so there is no comparison to make without your own test.
Which is cheaper, span-01 or xor?
span-01: $0.02 / $0 per 1M. xor: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run span-01 or xor locally?
xor yes — systemone pull juspay/xor downloads its weights. The other is only served as a hosted API.
JevBench public set (231 items), maker's self-run of Xor 1.2
