cogito-v1-preview-llama-3B: benchmark results
Provider: Nous Research. Released 2025-04-08. Access: Open.
Aggregate Rating 1377 ± 21, rank #6945 of 10916 rated models, from 330 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval Spanish Summarization - Mlsum ES | 29.67 | chrF3++ (%) | 95.9 |
| EuroEval Bosnian Summarization - LR SUM BS | 30.99 | chrF3++ (%) | 89.3 |
| aiXamine - Model & Data Privacy | 81.8 | Service score (0-100; normalized pass rate) | 87.8 |
| SLM-RAG Arena | 1576.1 | Elo Rating | 87.5 |
| EuroEval Catalan Summarization - Dacsa CA | 37.93 | chrF3++ (%) | 85.7 |
| EuroEval Ukrainian Summarization - LR SUM UK | 30.31 | chrF3++ (%) | 83.8 |
| EuroEval Portuguese NLU - ScaLA PT | 28.59 | Matthews correlation coefficient (%) | 83.6 |
| EuroEval Albanian Summarization - LR SUM SQ | 33.26 | chrF3++ (%) | 82 |
| EuroEval Serbian Summarization - LR SUM SR | 29.99 | chrF3++ (%) | 81 |
| EuroEval English Summarization - CNN Dailymail | 42.77 | chrF3++ (%) | 79 |
| EuroEval Norwegian Summarization - NO Sammendrag | 30.2 | chrF3++ (%) | 78.9 |
| EuroEval Estonian Summarization - ERR News | 30.21 | chrF3++ (%) | 78.5 |
Interactive version: theaggregate.ai/model?slug=cogito-v1-preview-llama-3b · How It Works · Data refreshed daily, snapshot 2026-11-08.