plamo-3-nict-2B-base: benchmark results
Provider: Other.
Aggregate Rating 1353 ± 40, rank #7630 of 10916 rated models, from 22 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Swallow - Pre-trained Japanese - WMT20 En-Ja | 27.2 | BLEU | 63.3 |
| Swallow - Pre-trained Japanese - NIILC | 54.8 | Character F1 (%) | 59.2 |
| Swallow - Pre-trained English - SQuAD2 | 53.1 | Exact Match (%) | 55.1 |
| Swallow - Pre-trained Japanese - JHumanEval | 29.5 | Pass@1 (%) | 44.9 |
| Swallow - Pre-trained Japanese - JSQuAD | 86.6 | Character F1 (%) | 38.8 |
| Swallow - Pre-trained Japanese - Average | 38.7 | Average Score (%) | 32.7 |
| Swallow - Pre-trained Japanese - JMMLU | 39.1 | Accuracy (%) | 32.7 |
| Swallow - Pre-trained Japanese - WMT20 Ja-En | 16.6 | BLEU | 32.7 |
| Swallow - Pre-trained Japanese - MGSM | 18.8 | Exact Match (%) | 29.6 |
| Swallow - Pre-trained Japanese - JEMHopQA | 44.7 | Character F1 (%) | 28.6 |
| Swallow - Pre-trained English - HumanEval | 25.1 | Pass@1 (%) | 24.5 |
| Swallow - Pre-trained English - MATH | 14 | Exact Match (%) | 23.5 |
Interactive version: theaggregate.ai/model?slug=plamo-3-nict-2b-base · How It Works · Data refreshed daily, snapshot 2026-11-08.