German Language LLM Index
a PeerBench project

Individual experiment result

GermEval NER (DE)

MiMo V2.5 Xiaomi

Micro-F1 excluding MISC reasoning off fp8
80.8%
Micro-F1 excluding MISC

Run details

Date
2026-08-11
Test cases
1,024
Median latency
0.86s
Total cost
$0.20
Avg. prompt tokens
1,529.5
Avg. answer tokens
26.2
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
xiaomi/mimo-v2.5
Run ID
2026-08-11T09-44-17__openrouter__xiaomi__mimo-v2.5__germeval_de