German Language LLM Index
a PeerBench project

Individual experiment result

INCLUDE (DE)

Claude Haiku 4.5 Anthropic

Exact match reasoning off provider-internal
68.3%
Exact match

Run details

Date
2026-06-02
Test cases
139
Median latency
3.45s
Total cost
$0.26
Avg. prompt tokens
154.6
Avg. answer tokens
347.4
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
2026-06-02T07-34-47__openrouter__anthropic__claude-haiku-4.5__include_de