German Language LLM Index
a PeerBench project

German LLM Benchmark · Model Profile

DeepSeek V4 Flash 0731

DeepSeekopen weights · MITfp4run 2026-08-11
1614

Elo

#7 among open-weights models

Benchmark breakdown

GermEval

82.0%

n=1024

Native German named-entity recognition — identify persons, locations, organisations and misc entities in German text, emitted as JSON. Scored with seqeval micro-F1 excluding the noisy MISC class. Run reasoning-off.

Named-entity recognitionnative · Native German
via GermEval (via EuroEval) ↗ View run details →

SB10K

61.2%

n=1024

Native German social-media sentiment classification — positive, neutral or negative. Human-annotated German text, not translated. Run reasoning-off; headline score is MCC on the predicted label.

3-class sentimentnative · Native German
via SB10K (via EuroEval) ↗ View run details →

ScaLA

76.1%

n=2048

Native German linguistic acceptability — does the sentence read as grammatical German (ja / nein)? Built from clean vs. minimally-corrupted German sentences. Run reasoning-off.

Binary acceptabilitynative · Native German
via ScaLA-de (via EuroEval) ↗ View run details →

Comparable models

Cost & speed

$0.075per 1,000 questions