German Language LLM Index
a PeerBench project

Individual experiment result

GermEval NER (DE)

DeepSeek V4 Pro 0813 DeepSeek

Micro-F1 excluding MISC reasoning off provider-internal
81.7%
Micro-F1 excluding MISC

Run details

Date
2026-08-13
Test cases
1,024
Median latency
1.61s
Total cost
$0.55
Avg. prompt tokens
1,181.2
Avg. answer tokens
25.9
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

Run ID
2026-08-13T09-02-33__openrouter__deepseek__deepseek-v4-pro-0813__germeval_de