plamo-3-nict-31B-base: benchmark results
Provider: Other.
Aggregate Rating 1550 ± 38, rank #1706 of 10916 rated models, from 22 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Swallow - Pre-trained English - SQuAD2 | 72.8 | Exact Match (%) | 100 |
| Swallow - Pre-trained Japanese - JSQuAD | 93.6 | Character F1 (%) | 100 |
| Swallow - Pre-trained Japanese - NIILC | 69.4 | Character F1 (%) | 98 |
| Swallow - Pre-trained Japanese - WMT20 En-Ja | 31.3 | BLEU | 94.9 |
| Swallow - Pre-trained Japanese - JEMHopQA | 62.5 | Character F1 (%) | 91.8 |
| Swallow - Pre-trained Japanese - Average | 58.3 | Average Score (%) | 89.8 |
| Swallow - Pre-trained English - BBH | 76.9 | Exact Match (%) | 85.7 |
| Swallow - Pre-trained Japanese - JCommonsenseQA | 95.5 | Accuracy (%) | 85.7 |
| Swallow - Pre-trained Japanese - MGSM | 68 | Exact Match (%) | 81.6 |
| Swallow - Pre-trained Japanese - JHumanEval | 50.7 | Pass@1 (%) | 80.6 |
| Swallow - Pre-trained Japanese - JMMLU | 67.9 | Accuracy (%) | 80.6 |
| Swallow - Pre-trained English - TriviaQA | 66.8 | Exact Match (%) | 79.6 |
Interactive version: theaggregate.ai/model?slug=plamo-3-nict-31b-base · How It Works · Data refreshed daily, snapshot 2026-11-08.