German Language LLM Index
a PeerBench project

Individual experiment result

GermEval NER (DE)

Gemini 3.8 Flash Google

Micro-F1 excluding MISC reasoning on / locked provider-internal
87.2%
Micro-F1 excluding MISC

Run details

Date
2026-09-04
Test cases
1,024
Median latency
2.78s
Total cost
$3.19
Avg. prompt tokens
1,060
Avg. answer tokens
26.2
Avg. reasoning tokens
176.7
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
2026-09-04T15-04-13__vertex_ai__gemini-3.8-flash__germeval_de