Shanghai AI Laboratory's multimodal decision model. A fine-tune of Qwen3.5-4B's language backbone (vision tower frozen) that answers up to 16 Choice, Score and Noul questions about a state and up to eight images in one forward pass, with a fitted calibration temperature.
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.
Decides
choice, score, noul, classify, route
noul, classify
Architecture
intern-decision
span
Fine-tuned from
qwen/qwen3.5-4b
—
License
apache-2.0
proprietary
Availability
Open weights
Hosted API
Hosted by
—
Respan
Input price
—
$0.020/MTok
Decision accuracy
80.6%
—
Calibration error
—
—
Valid action rate
—
—
Median latency
44 ms
—
p95 latency
44.6 ms
—
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 intern-decision and span-01?
intern-decision is from InternLM (Shanghai AI Laboratory) and span-01 from Respan. intern-decision has open weights you can download and run; span-01 is only available as a hosted API. Both answer noul and classify questions. Only intern-decision answers choice, score and route. intern-decision is licensed apache-2.0; span-01, proprietary.
Which is more accurate, intern-decision or span-01?
Only intern-decision publishes an accuracy figure (80.6% on LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions)); span-01 does not, so there is no comparison to make without your own test.
Which is cheaper, intern-decision or span-01?
intern-decision: Free (open weights). span-01: $0.02 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run intern-decision or span-01 locally?
intern-decision yes — systemone pull internlm/intern-decision downloads its weights. The other is only served as a hosted API.
Evaluation suite
LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions)
