Teuken-7B-base-v0.6: benchmark results

Provider: OpenGPT-X. Access: Open.

Aggregate Rating 1292 ± 34, rank #8722 of 10552 rated models, from 26 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Lara Mini Base Report (base-model protocol) - XNLI (English) (0-shot)56.9Accuracy (%), English benchmark99.1
Lara Mini Base Report (base-model protocol) - XNLI, All Languages (0-shot)42.8Accuracy (%) averaged over all languages/variants of the ben83.3
Lara Mini Base Report (base-model protocol) - COPA (0-shot)86Accuracy (%), English benchmark79.6
Lara Mini Base Report (base-model protocol) - HellaSwag (10-shot)77.4Accuracy normalized by answer length (%), English benchmark79.6
Lara Mini Base Report (base-model protocol) - T-HellaSwag, All Languages (0-shot)41.9Accuracy normalized by answer length (%) averaged over all l75
Lara Mini Base Report (base-model protocol) - Global PIQA (non-parallel), All Languages (0-shot)57.4Accuracy (%) averaged over all languages/variants of the ben72.2
Lara Mini Base Report (base-model protocol) - WinoGrande (5-shot)71.7Accuracy (%), English benchmark68.5
Lara Mini Base Report (base-model protocol) - PIQA (0-shot)78.7Accuracy normalized by answer length (%), English benchmark67.6
Lara Mini Base Report (base-model protocol) - XCOPA, All Languages (0-shot)57.8Accuracy (%) averaged over all languages/variants of the ben61.1
Lara Mini Base Report (base-model protocol) - Global PIQA (parallel), All Languages (0-shot)24.9Accuracy (%) averaged over all languages/variants of the ben58.3
Lara Mini Base Report (base-model protocol) - INCLUDE, All Languages (5-shot)40.4Accuracy (%) averaged over all languages/variants of the ben51.9
Lara Mini Base Report (base-model protocol) - ARC-Challenge (25-shot)54Accuracy normalized by answer length (%), English benchmark48.1

Interactive version: theaggregate.ai/model?slug=teuken-7b-base-v0-6 · How It Works · Data refreshed daily, snapshot 2026-11-16.