Teuken-7B-instruct-commercial-v0.4: benchmark results
Provider: OpenGPT-X. Access: Open.
Unified ELO 1332 ± 23, rank #1401 of 1632 rated models, from 184 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LA Leaderboard - RagQuAS | 80.5 | Semantic Answer Similarity (x100) | 86.8 |
| LA Leaderboard - QNLI Basque | 55.46 | Accuracy (%) | 86 |
| LA Leaderboard | 55.99 | Average Score (%) | 79.4 |
| LA Leaderboard - ClinDiagnosES | 59.73 | Semantic Answer Similarity (x100) | 77.6 |
| LA Leaderboard - ClinTreatES | 61.68 | Semantic Answer Similarity (x100) | 77.6 |
| LA Leaderboard - XL-Sum Spanish | 2.46 | BLEU | 77.6 |
| LA Leaderboard - OpenBookQA Spanish | 34 | Accuracy (%) | 77.2 |
| LA Leaderboard - PAWS-X Spanish | 64.05 | Accuracy (%) | 77.2 |
| LA Leaderboard - Summarization Galician | 5.58 | BLEU | 76.1 |
| LA Leaderboard - PAWS Galician | 63.35 | Accuracy (%) | 72.1 |
| LA Leaderboard - xStoryCloze Spanish | 68.23 | Accuracy (%) | 70.6 |
| LA Leaderboard - XNLI Galician | 46.46 | Accuracy (%) | 68.4 |
Interactive version: theaggregate.ai/model?slug=teuken-7b-instruct-commercial-v0-4 · How It Works · Data refreshed daily, snapshot 2026-10-08.