German Language LLM Index
a PeerBench project

Individual experiment result

GermEval NER (DE)

Qwen3 14B Alibaba

Micro-F1 excluding MISC reasoning off bf16
73.0%
Micro-F1 excluding MISC

Run details

Date
2026-06-11
Test cases
1,024
Median latency
21.12s
Total cost
Avg. prompt tokens
1,292.5
Avg. answer tokens
28.5
Avg. reasoning tokens
Quantization
bf16

About this benchmark

Native German named-entity recognition (person/location/org/misc) emitted as JSON; seqeval micro-F1 excluding MISC.

Named-entity recognition native · Native German Source ↗

Provenance

Canonical model
qwen/qwen3-14b
Run ID
2026-06-11T19-56-53__openai__qwen3-14b-bf16__germeval_de