Teuken-7B-Instruct-v0.4 — benchmark results
Provider: OpenGPT-X. Released 2024-11-26. Access: Open.
Unified ELO 1242 ± 33, rank #1635 of 1776 rated models, from 63 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LA Leaderboard - XNLI Galician | 48.97 | Accuracy (%) | 92.6 |
| LA Leaderboard | 57.03 | Average Score (%) | 86.8 |
| LA Leaderboard - COPA Spanish | 82.8 | Accuracy (%) | 75 |
| European LLM Leaderboard - Zero-Shot Accuracy | 48.22 | Average Accuracy (%) | 68.3 |
| LA Leaderboard - Spanish Law Exams | 32.77 | Accuracy (%) | 64.7 |
| EuroEval Portuguese NLU - MultiWikiQA PT | 70.1 | Reading comprehension Score (%) | 56.9 |
| LA Leaderboard - AQuAS | 65.91 | Accuracy (%) | 55.9 |
| EuroEval Finnish NLU - Tydiqa FI | 62.04 | Reading comprehension Score (%) | 52.5 |
| European LLM Leaderboard - Accuracy | 45.68 | Average Accuracy (%) | 49 |
| EuroEval Spanish NLU - MLQA ES | 59.32 | Reading comprehension Score (%) | 48.7 |
| EuroEval Italian NLU - SQuAD IT | 63.01 | Reading comprehension Score (%) | 43.8 |
| LA Leaderboard - GalCoLA | 51.14 | Accuracy (%) | 41.9 |
Interactive version: theaggregate.ai/model?slug=teuken-7b-instruct-v0-4 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.