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.
A Situated World Model for fast judgment in agent loops.
Decides
choice, score, noul, classify, route
choice, route, classify
Architecture
intern-decision
trio-spark
Fine-tuned from
qwen/qwen3.5-4b
—
License
apache-2.0
proprietary
Availability
Open weights
Hosted API
Hosted by
—
MachineFi
Input price
—
$0.042/MTok
Decision accuracy
80.6%
—
Calibration error
—
—
Valid action rate
—
—
Median latency
44 ms
—
p95 latency
44.6 ms
—
Evaluation suite
LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions)
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 trio-spark-v1?
intern-decision is from InternLM (Shanghai AI Laboratory) and trio-spark-v1 from MachineFi. intern-decision has open weights you can download and run; trio-spark-v1 is only available as a hosted API. Both answer choice, classify and route questions. Only intern-decision answers score and noul. intern-decision reads up to 8K tokens of state, against 1K tokens for trio-spark-v1. intern-decision is licensed apache-2.0; trio-spark-v1, proprietary.
Which is more accurate, intern-decision or trio-spark-v1?
Only intern-decision publishes an accuracy figure (80.6% on LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions)); trio-spark-v1 does not, so there is no comparison to make without your own test.
Which is cheaper, intern-decision or trio-spark-v1?
intern-decision: Free (open weights). trio-spark-v1: $0.042 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run intern-decision or trio-spark-v1 locally?
intern-decision yes — systemone pull internlm/intern-decision downloads its weights. The other is only served as a hosted API.
