Teuken-7B-Instruct-v0.4: benchmark results
Provider: OpenGPT-X. Released 2024-11-26. Access: Open.
Aggregate Rating 1330 ± 22, rank #1430 of 1656 rated models, from 144 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LA Leaderboard - ClinDiagnosES | 63.81 | Semantic Answer Similarity (x100) | 95.5 |
| LA Leaderboard - PAWS-X Spanish | 66.6 | Accuracy (%) | 92.6 |
| LA Leaderboard - XNLI Galician | 48.97 | Accuracy (%) | 92.6 |
| LA Leaderboard - PAWS Galician | 66.2 | Accuracy (%) | 91.2 |
| LA Leaderboard - RagQuAS | 80.63 | Semantic Answer Similarity (x100) | 89.7 |
| LA Leaderboard - TELEIA | 52.38 | Accuracy (%) | 84.6 |
| LA Leaderboard - XNLI Catalan | 49.4 | Accuracy (%) | 80.9 |
| LA Leaderboard - CatCoLA | 6.41 | MCC (x100) | 77.9 |
| LA Leaderboard - COPA Spanish | 82.8 | Accuracy (%) | 75 |
| LA Leaderboard - OpenBookQA Spanish | 33.8 | Accuracy (%) | 73.5 |
| LA Leaderboard - Parafraseja | 63.6 | Accuracy (%) | 73.5 |
| LA Leaderboard - TE-ca | 48.23 | Accuracy (%) | 72.1 |
Interactive version: theaggregate.ai/model?slug=teuken-7b-instruct-v0-4 · How It Works · Data refreshed daily, snapshot 2026-10-20.