GLiNER2 multi
FastinoOpen weights
The multilingual v1-generation GLiNER2 checkpoint.
- typed-decisions
- —
- Metatext suite
- 0.464
- ECE untuned
- 0.354
- p50 per case
- 202 ms
not run
2/7 over baseline
four CPU cores
Specifications
- Checkpoint
- fastino/gliner2-multi-v1
- Publisher
- Fastino
- Mechanism
- Schema-conditioned encoder (extraction + classification)
- Backbone
- mDeBERTa-v3 (span grid)
- Parameters
- 205M
- License
- Apache 2.0
- Runs as
- open weights, self-hosted
- Library
- gliner2
- Primitives
- Choice, Score, Noul, Extraction
- Pricing
- none — your compute
Metatext decisionsrank 17 of 21
Full leaderboard →Per-question accuracy — default payload, parallel mode, 120 judgments
| Task | Question | Type | Accuracy | Baseline | Beats? |
|---|---|---|---|---|---|
| agent_traces | outcome | choice | 0.500 | 0.357 | ✅ |
| agent_traces | needs_human | noul | 0.500 | 0.714 | ❌ |
| customer_service | department | choice | 0.800 | 0.400 | ✅ |
| customer_service | refund_requested | noul | 0.300 | 0.700 | ❌ |
| customer_service | frustration | score | 0.450 | 0.500 | ❌ |
| security_incidents | severity | choice | 0.188 | 0.312 | ❌ |
| security_incidents | actively_exploited | noul | 0.562 | 0.688 | ❌ |
Frequently asked questions
How does GLiNER2 multi compare to Jev?
On the Metatext suite GLiNER2 multi scores 0.464 against Jev's 0.863.
Is GLiNER2 multi open source?
Yes. fastino/gliner2-multi-v1 is released under Apache 2.0 and runs on your own hardware with the gliner2 library.
Can GLiNER2 multi extract entities?
Yes. GLiNER2 multi has a span head and scores 1.000 micro-F1 on the eight-case extraction task.