German Language LLM Index
a PeerBench project

Individual experiment result

GermEval NER (DE)

DeepSeek V4 Flash DeepSeek

Micro-F1 excluding MISC reasoning off bf16
80.2%
Micro-F1 excluding MISC

Run details

Date
2026-06-09
Test cases
1,024
Median latency
0.77s
Total cost
$0.18
Avg. prompt tokens
1,181.2
Avg. answer tokens
26.8
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

Run ID
2026-06-09T14-41-33__openrouter__deepseek__deepseek-v4-flash__germeval_de