German Language LLM Index
a PeerBench project

Individual experiment result

SB10K (DE)

Qwen3.6 27B (BF16) Alibaba

Matthews correlation coefficient reasoning off bf16
61.0%
Matthews correlation coefficient

Run details

Date
2026-08-15
Test cases
1,024
Median latency
1.59s
Total cost
Avg. prompt tokens
771.9
Avg. answer tokens
2.7
Avg. reasoning tokens
Quantization
bf16

About this benchmark

Native German Twitter sentiment (positive/neutral/negative), generate_until variant; primary metric MCC.

3-class sentiment native · Native German Source ↗

Provenance

Canonical model
qwen/qwen3.6-27b
Run ID
2026-08-15T09-27-06__openai__Qwen__Qwen3.6-27B__sb10k_de