German Language LLM Index
a PeerBench project

Individual experiment result

ScaLA (DE)

GPT-5.6 Luna OpenAI

Matthews correlation coefficient reasoning off provider-internal
72.2%
Matthews correlation coefficient

Run details

Date
2026-08-13
Test cases
2,048
Median latency
0.85s
Total cost
$0.19
Avg. prompt tokens
895.5
Avg. answer tokens
5.6
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
openai/gpt-5.6-luna
Run ID
2026-08-13T11-14-39__openrouter__openai__gpt-5.6-luna__scala_de