German Language LLM Index
a PeerBench project

Individual experiment result

GermEval NER (DE)

Tencent HY4-Preview Tencent

Micro-F1 excluding MISC reasoning off fp8
82.1%
Micro-F1 excluding MISC

Run details

Date
2026-08-30
Test cases
1,024
Median latency
1.86s
Total cost
Avg. prompt tokens
1,229.1
Avg. answer tokens
27.9
Avg. reasoning tokens
Quantization
fp8

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
tencent/hy4-preview
Run ID
2026-08-30T19-30-03__Tencent__tencent__hy4-preview__germeval_de