occiglot-7B-es-en-instruct: benchmark results
Provider: Occiglot. Released 2024-03-05. Access: Open.
Aggregate Rating 1375 ± 46, rank #7023 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LA Leaderboard - XNLI Spanish | 53.82 | Accuracy (%) | 100 |
| LA Leaderboard - XNLI Catalan | 52.01 | Accuracy (%) | 95.6 |
| LA Leaderboard - AQuAS | 69.94 | Semantic Answer Similarity (x100) | 91.2 |
| LA Leaderboard - Spanish Law Exams | 39.5 | Accuracy (%) | 88.2 |
| LA Leaderboard - OpenBookQA Galician | 29.2 | Accuracy (%) | 86.8 |
| LA Leaderboard - SIQA Catalan | 47.13 | Accuracy (%) | 86.8 |
| LA Leaderboard - PAWS Catalan | 67.7 | Accuracy (%) | 85.3 |
| LA Leaderboard - Parafraseja | 64.6 | Accuracy (%) | 85.3 |
| LA Leaderboard - Fake News Spanish | 73.78 | Accuracy (%) | 83.8 |
| LA Leaderboard - COPA Spanish | 84.2 | Accuracy (%) | 83.1 |
| LA Leaderboard - XL-Sum Spanish | 2.62 | BLEU | 82.8 |
| LA Leaderboard - EpecKorrefBin Basque | 55.03 | Accuracy (%) | 81.6 |
Interactive version: theaggregate.ai/model?slug=occiglot-7b-es-en-instruct · How It Works · Data refreshed daily, snapshot 2026-11-08.