Gemma-2-Llama-Swallow-9B-pt-v0.1: benchmark results
Provider: Google. Access: API.
Aggregate Rating 1524 ± 39, rank #2025 of 10916 rated models, from 22 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Swallow - Pre-trained Japanese - NIILC | 67.7 | Character F1 (%) | 95.9 |
| Swallow - Pre-trained Japanese - JEMHopQA | 64.3 | Character F1 (%) | 93.9 |
| Swallow - Pre-trained Japanese - WMT20 En-Ja | 30.4 | BLEU | 91.8 |
| Swallow - Pre-trained Japanese - WMT20 Ja-En | 24.7 | BLEU | 85.7 |
| Swallow - Pre-trained Japanese - JCommonsenseQA | 95 | Accuracy (%) | 81.6 |
| Swallow - Pre-trained English - XWINO | 90.6 | Accuracy (%) | 79.6 |
| Swallow - Pre-trained Japanese - Average | 55.8 | Average Score (%) | 77.6 |
| Swallow - Pre-trained English - HumanEval | 52.9 | Pass@1 (%) | 73.5 |
| Swallow - Pre-trained English - TriviaQA | 65.9 | Exact Match (%) | 71.4 |
| Swallow - Pre-trained Japanese - JMMLU | 65 | Accuracy (%) | 71.4 |
| Swallow - Pre-trained Japanese - JHumanEval | 46.2 | Pass@1 (%) | 70.4 |
| Swallow - Pre-trained English - HellaSwag | 60.2 | Accuracy (%) | 67.3 |
Interactive version: theaggregate.ai/model?slug=gemma-2-llama-swallow-9b-pt-v0-1 · How It Works · Data refreshed daily, snapshot 2026-11-08.