GLiNER2 benchmark
Fastino's small open encoder for entity and structured extraction, about 200 to 290 million parameters, text only. It returns spans with confidence scores. It can't read images or compute values that aren't printed, so those measurements show not supported rather than a score.
As of 20 Oct 2026, extractingbench has not published results for GLiNER2. It is in the planned lineup.
Facts
- Maker
- Fastino
- Input
- Text only
- Weights and licence
- Open, Apache 2.0
Providers each pair is benchmarked separately
- Fastino API serverless$0.03 per million input tokens, no output charge
- Hugging Face Inference Endpoints dedicatedper CPU hour
- Our Mac Mini (run it yourself) self-runno per-document price
Results by measurement
- Accuracy
- Accuracy
- Honesty about missing fields
- Null honesty
- False nulls
- Confidence you can trust
- Calibration error
- 80% range coverage
- Messy-input robustness
- Messy-input drop
- Long and large documents
- Long-document drop
- Many-fields drop
- Formats and languages
- Accuracy across locales
- Non-English accuracy
- Consistency
- Answers that change on a rerun
- Text and image agree
- Answers that change when fields are renamed or reordered
- Math
- Math, one step
- Math, multi-step
- Pointing
- Pointing
- Safety
- Hijack rate
- Speed and cost
- Latency, median
- Latency, p90
- Throughput
- Cost per 1,000 documents
First results coming