German Language LLM Index
a PeerBench project

Individual experiment result

ScaLA (DE)

GPT-5.5 OpenAI

Matthews correlation coefficient reasoning on / locked provider-internal
79.7%
Matthews correlation coefficient

Run details

Date
2026-06-13
Test cases
2,048
Median latency
1.52s
Total cost
$11.05
Avg. prompt tokens
913.2
Avg. answer tokens
6
Avg. reasoning tokens
21.6
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
openai/gpt-5.5
Run ID
2026-06-13T12-23-33__openai__codex__gpt-5.5-low__scala_de