German Language LLM Index
a PeerBench project

Individual experiment result

ScaLA (DE)

Gemma 4 26B A4B Google

Matthews correlation coefficient reasoning off provider-internal
66.3%
Matthews correlation coefficient

Run details

Date
2026-06-08
Test cases
2,048
Median latency
0.46s
Total cost
$0.28
Avg. prompt tokens
910.7
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

Run ID
2026-06-08T16-45-24__vertex_ai__openai__google__gemma-4-26b-a4b-it-maas__scala_de