GLiNER2.5-Decide launches: 340M classifier beats LLM routers on multi-task decisions
philipvollet · x · 2026-09-25
fastino has released GLiNER2.5-Decide, a 340M-parameter English encoder tuned for operational decision tasks.
- Any label set at call time: intent, routing, priority, sentiment, and multi-label tagging in a single forward pass — no prompt templates, no generated tokens; it can also return character-level spans, relations, and structured records.
- Benchmark: on fastino/fast-decisions (17 domains, 300 held-out examples each), it averages 60.2% exact-match accuracy, beating its own 1B variant (59.6%) and rivals like JevK5, SemIf (Qwen3.5-4B), and GLiFormer large-v1.
- A 287M multilingual variant, GLiNER2.5-multi-Decide, covers non-English inputs.
- Explicitly not general-purpose: it targets customer/banking intent, ticket routing, moderation, severity, and agent-completion decisions. Weights are Apache-2.0 on Hugging Face, with hosted inference and a fine-tuning API usable inside coding agents.
More from Models
- Robot build test: GPT-6 Astra stabilizes two-board structure, Claude Fable 5.2 falls short — qinzytech · 2026-11-12
- Zvi dissects Anthropic's latest system card, disputing the autonomy threshold call — Don't Worry About the Vase (Zvi) · 2026-11-12
- Unsloth ships Qwen3.8-27B Dynamic V3.1 GGUFs with 5-10% accuracy gains — danielhanchen · 2026-11-12
- antirez backs low-bit DeepSeek 4.1 Flash over Qwen 27B dense on Apple M5 Macs — antirez · 2026-11-12
- Gemini re-renders images as text when vision is removed, dropping only 6% WSR — zacharynado · 2026-11-12
- Bare-harness coding benchmark: Fable 5.2 best overall, Gemini 4 Carbon best value — Semantic_meaning · 2026-11-12