Comparison · ReDefiNER

ReDefiNER vs GLiNER

Updated 19 November 2026, by Jungroo AI Labs, the makers of ReDefiNER

Both are open models that find the entity types you choose when you run them, with no retraining, and both run on a CPU. GLiNER matches text against type names. ReDefiNER reads a rulebook: a one-line description and optional rules for each type. On the same 7 test sets, ReDefiNER scored 63.1 F1 with descriptions against GLiNER's 61.7. With type names alone, GLiNER scored 61.6 against ReDefiNER's 56.2. We make ReDefiNER, and we ran both models ourselves.

The short answer

  • Choose GLiNER when your types are clear from their names (person, company, city), when you want a smaller and widely used model, or when you don't want to write descriptions.
  • Choose ReDefiNER when a type needs explaining, or needs rules such as “leave out titles”, “never label our own brand” or “a reference starting with # is an order number”, and when you want to change what counts by editing text.
  • Test both on 20 to 50 of your own sentences. On a single dataset the gap can be much larger than these averages, in either direction.

Accuracy on the same test

Mean F1 over the 7 CrossNER and MIT test sets (AI, literature, music, politics, science, movies and restaurants; 6,470 sentences). Each type was given either as a one-line description or by its name alone. For GLiNER and NuNER, the first number uses the model's default threshold and the second a threshold chosen on the dev sets. ReDefiNER uses its one fixed release setting.

ModelWith descriptionsNames only
ReDefiNER 0.8B63.156.2
GLiNER large v2.5, our run61.7 / 62.261.6 / 63.1
NuNER Zero-span 0.4B, our run26.5 / 55.562.6 / 62.6
GNER-T5-large 0.78B, as reported–63.5

F1 counts a prediction as right only when both the span and the type match exactly. GLiNER and NuNER were run through the gliner library 0.2.29 on the same sentences, with each type's description, or its name, as the label. Full tables, settings and rulebooks.

In short: with descriptions, ReDefiNER is ahead of GLiNER at either threshold. GLiNER's best setting (names only, threshold tuned on dev data) ties ReDefiNER's best at 63.1. With names alone, ReDefiNER is the weakest model in this table.

How they differ

GLiNER large v2.5ReDefiNER
What you give itA list of type names (labels)A rulebook: types, a one-line description each, numbered rules and optional examples
Rules such as “leave out titles”No place to state them, beyond the label textWritten in plain English. Which rules work
How it worksA bidirectional encoder that matches text spans against the labelsA 0.8B language-model backbone with span and type heads. Non-generative: it never writes text
What it returnsSpans with a label and a scoreExact character spans, each with a type and a confidence
SizeA smaller encoder model0.8 billion parameters, one 0.77 GB int8 file
LicenceApache 2.0 (per its model card)Apache 2.0

Where ReDefiNER is weaker

  • Type names alone. 56.2 against GLiNER's 61.6. Always write a one-line description for each type.
  • Abstaining. When a type's condition isn't clearly met, it tends to label anyway.
  • Rules against a strong prior are mostly ignored, such as relabelling a person's name as something other than a person, or “only revenue amounts, not every money amount”.
  • Limits. English only, and spans of up to 16 tokens in release 1.0.8.
  • Speed. On a 4-core CPU server, each sentence takes about 0.4 seconds once the rulebook is loaded; reading a new rulebook of about 1,000 tokens takes 4 to 5 seconds first. We have not timed GLiNER on the same machine.

Try both on your own text

Both install with pip and run on a CPU. Give GLiNER your type names, and give ReDefiNER the same types with a one-line description each:

pip install gliner redefiner
from gliner import GLiNER
gliner = GLiNER.from_pretrained("gliner-community/gliner_large-v2.5")
gliner.predict_entities(text, ["person", "organization"], threshold=0.5)

from redefiner import Tagger
tagger = Tagger.from_pretrained("jungroo-ai/redefiner-0.8b")
tagger.extract(text, """[RULES]
Extract every entity of the supplied types. Return exact spans from the text.

[TYPE] PERSON
[DESCRIPTION] A person's name.
PE1 Label the full name; leave out titles such as "Dr" or "Prof".

[TYPE] ORGANIZATION
[DESCRIPTION] A company, university or other institution.
""")

Questions

Frequently asked.

Is ReDefiNER more accurate than GLiNER?

With one-line type descriptions, yes on our 7-set test: 63.1 against 61.7 F1, or 62.2 with GLiNER's threshold tuned. With type names only, no: GLiNER scored 61.6, or 63.1 tuned, against ReDefiNER's 56.2.

Can GLiNER follow written rules?

GLiNER matches text against labels, so a rule has to fit into the label itself. Newer models such as GLiNER2 accept a description per label; we have not run GLiNER2 on this extraction test.

Do both run on a CPU?

Yes. ReDefiNER needs about 2 to 2.6 GB of memory at peak. Once its rulebook is loaded it takes about 0.4 to 0.7 seconds per sentence on a 4-core server or an Apple M2, and 1.3 seconds on a 2-vCPU server.

Are both free for commercial use?

Both are released under Apache 2.0: ReDefiNER's code and weights, and GLiNER large v2.5 according to its model card.

Does ReDefiNER generate text like an LLM?

No. Like GLiNER, it marks exact spans of your text and never writes new text, so it cannot invent an entity that isn't in the input.

Try it on your own text

Test ReDefiNER on 20 of your sentences.

The live demo runs on a CPU. Edit a rule and see the output change, or write to us and we will test a rulebook on your data.

Contact

Tell us what you need.

We partner with a limited number of enterprises at a time, so every engagement gets senior attention. Tell us what you want to build, and our leadership will reply.

We use these details only to reply to you. What you type is saved as you go, so we can still reply if you leave before pressing Send. Privacy

General enquiries

Jungroo AI Labs

Partnerships, projects and products

Leadership

Sethuraman T A

Chief Executive Officer

Engineering

Cibe Hariharan

Chief Technology Officer