German Language LLM Index
a PeerBench project

Individual experiment result

ScaLA (DE)

Gemini 3 Flash Preview Google

Matthews correlation coefficient reasoning off provider-internal
77.0%
Matthews correlation coefficient

Run details

Date
2026-06-25
Test cases
2,048
Median latency
0.94s
Total cost
$0.81
Avg. prompt tokens
777.7
Avg. answer tokens
1.5
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
2026-06-25T11-34-32__vertex_ai__gemini-3-flash-preview__scala_de