cogito-v2-preview-llama-70B: benchmark results
Provider: Nous Research. Released 2025-07-31. Access: Open.
Aggregate Rating 1616 ± 28, rank #870 of 10916 rated models, from 271 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval Hungarian NLU - HuSST | 67.81 | Matthews correlation coefficient (%) | 100 |
| EuroEval Spanish NLU - Sentiment Headlines ES | 54.13 | Matthews correlation coefficient (%) | 100 |
| EuroEval Norwegian Summarization - NO Sammendrag | 32.32 | chrF3++ (%) | 99.4 |
| EuroEval Estonian Summarization - ERR News | 32.71 | chrF3++ (%) | 99.3 |
| EuroEval Romanian NLU - RoSent | 98.46 | Matthews correlation coefficient (%) | 99 |
| EuroEval Spanish Summarization - Mlsum ES | 30.92 | chrF3++ (%) | 98.6 |
| EuroEval Serbian NLU - MMS SR | 52.22 | Matthews correlation coefficient (%) | 98.5 |
| EuroEval Catalan Summarization - Dacsa CA | 39.48 | chrF3++ (%) | 98.1 |
| EuroEval Danish Summarization - Nordjylland News | 37.99 | chrF3++ (%) | 98.1 |
| EuroEval English Common Sense Reasoning | 89.3 | Common Sense Reasoning Average Score (%) | 98.1 |
| EuroEval Czech Common Sense Reasoning | 81.04 | Common Sense Reasoning Average Score (%) | 97.6 |
| EuroEval Greek NLU - Greek SA | 82.79 | Matthews correlation coefficient (%) | 97.5 |
Interactive version: theaggregate.ai/model?slug=cogito-v2-preview-llama-70b · How It Works · Data refreshed daily, snapshot 2026-11-08.