Llama-Poro-2-70B-Instruct: benchmark results
Provider: Meta. Released 2025-05-01. Access: Open.
Aggregate Rating 1598 ± 27, rank #1032 of 10916 rated models, from 116 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval Swedish NLU - Swerec | 80.75 | Matthews correlation coefficient (%) | 98.5 |
| EuroEval German NLU - Sb10K | 60.94 | Matthews correlation coefficient (%) | 96.6 |
| EuroEval Finnish NLU - Scandisent FI | 93.1 | Matthews correlation coefficient (%) | 96.3 |
| EuroEval Finnish NLU - ScaLA FI | 46.71 | Matthews correlation coefficient (%) | 96.2 |
| EuroEval Norwegian NLU - Norec | 62.03 | Matthews correlation coefficient (%) | 94.7 |
| EuroEval Danish NLU - Angry Tweets | 58.55 | Matthews correlation coefficient (%) | 94.5 |
| EuroEval Finnish | 63.82 | Average Score (%) | 92 |
| EuroEval Italian NLU - Sentipolc16 | 65.89 | Matthews correlation coefficient (%) | 90.3 |
| EuroEval Finnish NLU | 64.94 | NLU Average Score (%) | 89.3 |
| EuroEval Faroese | 56.03 | Average Score (%) | 88 |
| EuroEval Italian Common Sense Reasoning | 69.47 | Common Sense Reasoning Average Score (%) | 88 |
| EuroEval Faroese NLU - FoSent | 60.47 | Matthews correlation coefficient (%) | 87.2 |
Interactive version: theaggregate.ai/model?slug=llama-poro-2-70b-instruct · How It Works · Data refreshed daily, snapshot 2026-11-08.