German Language LLM Index
a PeerBench project

Individual experiment result

ScaLA (DE)

Tencent HY3-Preview Tencent

Matthews correlation coefficient reasoning off provider-internal
62.5%
Matthews correlation coefficient

Run details

Date
2026-06-09
Test cases
2,048
Median latency
2.48s
Total cost
$0.13
Avg. prompt tokens
1,027.6
Avg. answer tokens
2.6
Avg. reasoning tokens
Quantization
provider-internal

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/hy3-preview
Run ID
2026-06-09T15-59-54__openrouter__tencent__hy3-preview__scala_de