German Language LLM Index
a PeerBench project

Individual experiment result

ScaLA (DE)

Tencent HY4-Preview Tencent

Matthews correlation coefficient reasoning off fp8
74.0%
Matthews correlation coefficient

Run details

Date
2026-08-30
Test cases
2,048
Median latency
1.56s
Total cost
Avg. prompt tokens
1,063.5
Avg. answer tokens
2.6
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
tencent/hy4-preview
Run ID
2026-08-30T19-30-04__Tencent__tencent__hy4-preview__scala_de