German Language LLM Index
a PeerBench project

Individual experiment result

GermEval NER (DE)

Gemma 4 26B A4B Google

Micro-F1 excluding MISC reasoning off provider-internal
81.8%
Micro-F1 excluding MISC

Run details

Date
2026-06-08
Test cases
1,024
Median latency
1.14s
Total cost
$0.19
Avg. prompt tokens
1,153
Avg. answer tokens
30.3
Avg. reasoning tokens
Quantization
provider-internal

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

Run ID
2026-06-08T16-55-13__vertex_ai__openai__google__gemma-4-26b-a4b-it-maas__germeval_de