GLiNER-2.5-Decide

​

Model capabilities and use cases

1. Model routing. Route requests by destination, complexity, or escalation level. Return the selected route with probabilities and confidence scores.
2. Tool calling. Select from a permitted set of tools and capture arguments from the request as structured records.
3. Browser and computer use. Evaluate the current state to select the next action. Represent the action, target, and parameters as a structured record.
4. Guardrails. Evaluate safety, harm type, and escalation together, extracting harmful spans verbatim. Apply constraints when combinations of answers would be contradictory.
5. Context pruning. Decide which information in the context is relevant and return the exact character spans associated with that decision.
6. LLM-as-a-judge. Express rubric criteria as categorical or ordinal questions. Return selected values with probability distributions and confidence scores.
7. Games and simulations. Evaluate game state to determine intent, action, or outcome. Represent actors and state information through entities, relations, and structured records.