Llama-3.1-Tulu-3.1-8B: benchmark results
Provider: Allen AI. Released 2025-02-07. Access: Open.
Aggregate Rating 1444 ± 36, rank #4027 of 10916 rated models, from 41 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval Dutch NLU - DBRD | 91.36 | Matthews correlation coefficient (%) | 85.7 |
| EuroEval Italian NLU - ScaLA IT | 33.58 | Matthews correlation coefficient (%) | 81.3 |
| EuroEval Spanish NLU - Sentiment Headlines ES | 45.54 | Matthews correlation coefficient (%) | 71.6 |
| EuroEval Finnish NLU - Scandisent FI | 90.66 | Matthews correlation coefficient (%) | 70.6 |
| EuroEval Italian NLU | 54.5 | NLU Average Score (%) | 68.7 |
| EuroEval Italian NLU - Sentipolc16 | 57.49 | Matthews correlation coefficient (%) | 68.4 |
| EuroEval Spanish NLU | 47.97 | NLU Average Score (%) | 68.3 |
| EuroEval Portuguese NLU - HAREM | 46.41 | Micro F1 excluding MISC (%) | 67.7 |
| EuroEval Portuguese NLU | 52.59 | NLU Average Score (%) | 64.2 |
| EuroEval Portuguese NLU - SST-2 PT | 79.79 | Matthews correlation coefficient (%) | 64.1 |
| EuroEval Spanish NLU - ScaLA ES | 24.51 | Matthews correlation coefficient (%) | 63.7 |
| EuroEval Spanish | 45.65 | Average Score (%) | 62 |
Interactive version: theaggregate.ai/model?slug=llama-3-1-tulu-3-1-8b · How It Works · Data refreshed daily, snapshot 2026-11-08.