German Language LLM Index
a PeerBench project

Individual experiment result

ScaLA (DE)

MiMo V2.5 Pro Xiaomi

Matthews correlation coefficient reasoning off fp8
74.8%
Matthews correlation coefficient

Run details

Date
2026-06-09
Test cases
2,048
Median latency
0.57s
Total cost
$2.33
Avg. prompt tokens
1,301
Avg. answer tokens
2.5
Avg. reasoning tokens
Quantization
fp8

About this benchmark

Native German linguistic acceptability — is the sentence grammatical (ja/nein)? generate_until; primary metric MCC (accuracy recorded as secondary).

Binary acceptability native · Native German Source ↗

Provenance

Canonical model
xiaomi/mimo-v2.5-pro
Run ID
2026-06-09T15-24-43__openrouter__xiaomi__mimo-v2.5-pro__scala_de