Bielik-11B-v3.1-Instruct: benchmark results

Provider: SpeakLeash. Access: Open.

Aggregate Rating 1576 ± 50, rank #1221 of 10556 rated models, from 8 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
PLCC - Art & Entertainment70Accuracy (%)64.9
PLCC - Culture & Tradition76Accuracy (%)59.5
PLCC - Geography85Accuracy (%)59.3
PLCC - History84Accuracy (%)58.3
PLCC - Overall72Mean category accuracy (%)54.8
PLCC - Vocabulary64Accuracy (%)52.2
PLCC - Grammar58Accuracy (%)35.7
Last Translation Benchmark0.88Verified Translations (%)15.7

Interactive version: theaggregate.ai/model?slug=bielik-11b-v3-1-instruct · How It Works · Data refreshed daily, snapshot 2026-11-17.