German Language LLM Index
a PeerBench project

Individual experiment result

MuSR (DE)

Gemma 4 31B Google

Accuracy reasoning off bf16
83.5%
Accuracy

Run details

Date
2026-06-11
Test cases
564
Median latency
23.30s
Total cost
$0.23
Avg. prompt tokens
1,477.9
Avg. answer tokens
650.1
Avg. reasoning tokens
Quantization
bf16

About this benchmark

German MuSR v1.1 defect-filtered benchmark: 553 questions (11 truncated team-allocation translations excluded), generate_until cot+; primary metric accuracy.

2–5 option multiple choice translated · German translation Source ↗

Subject breakdown

Subject Score
murder mystery 86.4%
object placements 76.6%
team allocation 82.4%

Provenance

Canonical model
google/gemma-4-31b-it
Run ID
2026-06-11T14-02-37__openai__gemma-4-31b-it-bf16__musr_de