German Language LLM Index
a PeerBench project

Individual experiment result

INCLUDE (DE)

Tencent HY3 Tencent

Exact match reasoning off fp8
83.2%
Exact match

Run details

Date
2026-08-30
Test cases
107
Median latency
2.73s
Total cost
Avg. prompt tokens
147
Avg. answer tokens
150.3
Avg. reasoning tokens
Quantization
fp8

About this benchmark

INCLUDE-DE v1.2: 107 valid German questions after a blinded semantic audit excluded 32 duplicate, wrong-keyed, non-unique, corrupted, or underspecified source rows consistently; strict final-answer parsing; primary metric exact match.

4-option multiple choice native · Native German Source ↗

Provenance

Canonical model
tencent/hy3
Run ID
2026-08-30T19-46-08__Tencent__tencent__hy3__include_de