German Language LLM Index
a PeerBench project

Individual experiment result

SB10K (DE)

Tencent HY3 Tencent

Matthews correlation coefficient reasoning off fp8
62.4%
Matthews correlation coefficient

Run details

Date
2026-08-30
Test cases
1,024
Median latency
1.43s
Total cost
Avg. prompt tokens
888.4
Avg. answer tokens
2.6
Avg. reasoning tokens
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
tencent/hy3
Run ID
2026-08-30T19-46-08__Tencent__tencent__hy3__sb10k_de