cogito-v1-preview-llama-8B: benchmark results
Provider: Nous Research. Released 2025-04-08. Access: Open.
Aggregate Rating 1464 ± 20, rank #3082 of 10916 rated models, from 329 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval Spanish Summarization - Mlsum ES | 29.93 | chrF3++ (%) | 97.3 |
| EuroEval Catalan Summarization - Dacsa CA | 39.05 | chrF3++ (%) | 95.5 |
| EuroEval Norwegian Summarization - NO Sammendrag | 31.42 | chrF3++ (%) | 95.5 |
| EuroEval Serbian Summarization - LR SUM SR | 30.76 | chrF3++ (%) | 95.2 |
| EuroEval Bosnian Summarization - LR SUM BS | 31.26 | chrF3++ (%) | 93.9 |
| EuroEval French NLU - ScaLA FR | 58.23 | Matthews correlation coefficient (%) | 92 |
| EuroEval Estonian Summarization - ERR News | 31.37 | chrF3++ (%) | 91.9 |
| EuroEval Albanian Summarization - LR SUM SQ | 33.82 | chrF3++ (%) | 91.2 |
| EuroEval Hungarian NLU - HuSST | 59.96 | Matthews correlation coefficient (%) | 91.1 |
| EuroEval Danish Summarization - Nordjylland News | 37.29 | chrF3++ (%) | 90.5 |
| EuroEval Dutch Simplification - Duidelijke Taal | 54.98 | Score (%) | 90.3 |
| EuroEval Portuguese NLU - ScaLA PT | 39.47 | Matthews correlation coefficient (%) | 89.5 |
Interactive version: theaggregate.ai/model?slug=cogito-v1-preview-llama-8b · How It Works · Data refreshed daily, snapshot 2026-11-08.