German Language LLM Index
a PeerBench project

Individual experiment result

SB10K (DE)

MiMo V2.5 Xiaomi

Matthews correlation coefficient reasoning off fp8
61.2%
Matthews correlation coefficient

Run details

Date
2026-08-11
Test cases
1,024
Median latency
0.62s
Total cost
$0.14
Avg. prompt tokens
1,136.3
Avg. answer tokens
2.8
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
xiaomi/mimo-v2.5
Run ID
2026-08-11T10-48-40__openrouter__xiaomi__mimo-v2.5__sb10k_de