German Language LLM Index
a PeerBench project

Individual experiment result

SB10K (DE)

Gemma 4 12B Google

Matthews correlation coefficient reasoning off bf16
62.2%
Matthews correlation coefficient

Run details

Date
2026-06-11
Test cases
1,024
Median latency
21.45s
Total cost
Avg. prompt tokens
758.7
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
google/gemma-4-12b-it
Run ID
2026-06-11T14-40-46__openai__gemma4-12b-bf16__sb10k_de