German Language LLM Index
a PeerBench project

Individual experiment result

INCLUDE (DE)

Claude Sonnet 5 Anthropic

Exact match reasoning off provider-internal
72.7%
Exact match

Run details

Date
2026-07-21
Test cases
139
Median latency
4.92s
Total cost
$0.64
Avg. prompt tokens
229.9
Avg. answer tokens
263.5
Avg. reasoning tokens
Quantization
provider-internal

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

Run ID
2026-07-21T11-51-21__openai__cc__claude-sonnet-5__include_de