Hanno Labs' small calibrated decision model. A LoRA on Qwen3-1.7B plus trained decision-token embeddings with stable slots, returning the full distribution over up to 255 caller-defined choices and a null slot for Choice, Score and Noul questions.
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.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
bosun
intern-decision
Fine-tuned from
qwen/qwen3-1.7b
qwen/qwen3.5-4b
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
84.9%
80.6%
Calibration error
0.050
—
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 bosun and intern-decision?
bosun is from Hanno Labs and intern-decision from InternLM (Shanghai AI Laboratory). Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. bosun is the smaller model, at 2.0B parameters to 4.5B.
Which is more accurate, bosun or intern-decision?
They report on different suites — bosun 84.9% on DecisionBench (Hanno-Labs/decision-bench, 23,900 rows; seen task families), intern-decision 80.6% on LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, bosun or intern-decision?
bosun: Free (open weights). intern-decision: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run bosun or intern-decision locally?
Yes, both: systemone pull hanno-labs/bosun and systemone pull internlm/intern-decision download the weights.
Evaluation suite
DecisionBench (Hanno-Labs/decision-bench, 23,900 rows; seen task families)
LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions)
