German Language LLM Index
a PeerBench project

Individual experiment result

SB10K (DE)

GLM-5.3 Flash Z.ai

Matthews correlation coefficient reasoning on / locked fp8
63.6%
Matthews correlation coefficient

Run details

Date
2026-08-30
Test cases
1,024
Median latency
3.42s
Total cost
Avg. prompt tokens
785.3
Avg. answer tokens
4
Avg. reasoning tokens
97.2
Quantization
fp8

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
z-ai/glm-5.3-flash
Run ID
2026-08-30T15-44-43__openrouter__z-ai__glm-5.3-flash__sb10k_de