alfred-40B-1023: benchmark results
Provider: LightOn. Released 2023-10-23. Access: Open.
Aggregate Rating 1374 ± 35, rank #7056 of 10916 rated models, from 94 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval French NLU - FQuAD | 75.13 | Character F1 (%) | 94.5 |
| EuroEval English NLU - SQuAD | 85.49 | Character F1 (%) | 88.3 |
| EuroEval German NLU - Germanquad | 64.26 | Character F1 (%) | 86.6 |
| EuroEval Swedish NLU - Swerec | 78.56 | Matthews correlation coefficient (%) | 85.4 |
| EuroEval Dutch NLU - SQuAD NL | 76.32 | Character F1 (%) | 75.3 |
| EuroEval Italian NLU - ScaLA IT | 26.86 | Matthews correlation coefficient (%) | 69.5 |
| EuroEval Spanish NLU - ScaLA ES | 24.09 | Matthews correlation coefficient (%) | 63.5 |
| EuroEval Italian NLU | 52.22 | NLU Average Score (%) | 61.6 |
| EuroEval Norwegian Knowledge | 22.26 | Knowledge Average Score (%) | 59.4 |
| EuroEval Italian NLU - Sentipolc16 | 53.51 | Matthews correlation coefficient (%) | 58.9 |
| EuroEval German NLU - Sb10K | 52.46 | Matthews correlation coefficient (%) | 58.5 |
| EuroEval French NLU | 62.16 | NLU Average Score (%) | 57.4 |
Interactive version: theaggregate.ai/model?slug=alfred-40b-1023 · How It Works · Data refreshed daily, snapshot 2026-11-08.