German Language LLM Index
a PeerBench project

Individual experiment result

GermEval NER (DE)

Qwen3.8 Flash Alibaba

Micro-F1 excluding MISC reasoning off provider-internal
79.1%
Micro-F1 excluding MISC

Run details

Date
2026-10-15
Test cases
1,024
Median latency
0.99s
Total cost
$0.20
Avg. prompt tokens
1,199.3
Avg. answer tokens
24.9
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

Canonical model
qwen/qwen3.8-flash
Run ID
2026-10-15T20-56-36__openrouter__qwen__qwen3.8-flash__germeval_de