German Language LLM Index
a PeerBench project

Individual experiment result

GermEval NER (DE)

DeepSeek V4 Pro DeepSeek

Micro-F1 excluding MISC reasoning off fp8
82.2%
Micro-F1 excluding MISC

Run details

Date
2026-06-09
Test cases
1,024
Median latency
1.74s
Total cost
$2.02
Avg. prompt tokens
1,181.2
Avg. answer tokens
26.3
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

Run ID
2026-06-09T15-18-51__openrouter__deepseek__deepseek-v4-pro__germeval_de