German Language LLM Index
a PeerBench project

Individual experiment result

MMLU-ProX (DE)

Gemini 3.6 Flash Google

Exact match reasoning off provider-internal
86.0%
Exact match

Run details

Date
2026-07-23
Test cases
11,759
Median latency
1.84s
Total cost
$52.23
Avg. prompt tokens
1,664.9
Avg. answer tokens
259.2
Avg. reasoning tokens
Quantization
provider-internal

About this benchmark

German MMLU-ProX across 14 subjects; primary metric accuracy. Legacy rows have 11,759 items. Corrected v1.1 rows have 11,737 after a frozen, model-independent manifest excludes 20 duplicated-gold translation collisions, one independently reviewed ambiguous source item, and one independently confirmed notation-translation collapse; the row's item count identifies the definition.

10-option multiple choice translated · Professional translation Source ↗

Subject breakdown

Subject Score
biology 92.6%
business 88.2%
chemistry 88.3%
computer science 88.5%
economics 88.7%
engineering 80.5%
health 79.3%
history 80.1%
law 73.2%
math 93.9%
other 81.5%
philosophy 82.4%
physics 90.4%
psychology 87.3%

Provenance

Run ID
2026-07-23T00-09-20__vertex_ai__gemini-3.6-flash__mmlu_prox_de