plamo-2-8B: benchmark results
Provider: Other. Access: Open.
Unified ELO 1507 ± 45, rank #1049 of 2656 rated models, from 26 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| pfgen-bench - Completion Mode - Truthfulness | 0.94 | Truthfulness Score | 98.7 |
| pfgen-bench - Completion Mode - Fluency | 0.86 | Fluency Score | 97.1 |
| pfgen-bench - Completion Mode - Score | 0.75 | pfgen Score (mean of three) | 96.5 |
| pfgen-bench - Completion Mode - Helpfulness | 0.46 | Helpfulness Score | 94.1 |
| Swallow - Pre-trained Japanese - NIILC | 65.5 | Character F1 (%) | 85.7 |
| Swallow - Pre-trained Japanese - WMT20 En-Ja | 28 | BLEU | 71.4 |
| Swallow - Pre-trained Japanese - JSQuAD | 91 | Character F1 (%) | 66.3 |
| Swallow - Pre-trained Japanese - JCommonsenseQA | 90.9 | Accuracy (%) | 61.2 |
| Swallow - Pre-trained Japanese - MGSM | 50.8 | Exact Match (%) | 61.2 |
| Swallow - Pre-trained English - TriviaQA | 58.4 | Exact Match (%) | 55.1 |
| Swallow - Pre-trained Japanese - Average | 48.1 | Average Score (%) | 55.1 |
| Swallow - Pre-trained Japanese - JMMLU | 53.6 | Accuracy (%) | 55.1 |
Interactive version: theaggregate.ai/model?slug=plamo-2-8b · How It Works · Data refreshed daily, snapshot 2026-09-19.