German Language LLM Index
a PeerBench project

Individual experiment result

ScaLA (DE)

Gemini 3.7 Flash Google

Matthews correlation coefficient reasoning on / locked provider-internal
79.1%
Matthews correlation coefficient

Run details

Date
2026-08-14
Test cases
2,048
Median latency
2.18s
Total cost
$1.60
Avg. prompt tokens
777.7
Avg. answer tokens
1.5
Avg. reasoning tokens
51.1
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
2026-08-14T13-26-58__vertex_ai__gemini-3.7-flash__scala_de