German Language LLM Index
a PeerBench project

Individual experiment result

ScaLA (DE)

Qwen3.6 35B-A3B Alibaba

Matthews correlation coefficient reasoning off fp8
64.2%
Matthews correlation coefficient

Run details

Date
2026-06-09
Test cases
2,048
Median latency
0.51s
Total cost
$0.29
Avg. prompt tokens
928.9
Avg. answer tokens
2.6
Avg. reasoning tokens
Quantization
fp8

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
qwen/qwen3.6-35b-a3b
Run ID
2026-06-09T16-55-32__openrouter__qwen__qwen3.6-35b-a3b__scala_de