Qwen-3-Swallow-32B-CPT-v0.2: benchmark results
Provider: Alibaba.
Aggregate Rating 1569 ± 37, rank #1417 of 10916 rated models, from 35 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Swallow - Post-trained Japanese - WMT20 Ja-En | 22.8 | BLEU | 72.4 |
| Swallow - Post-trained English - HellaSwag | 90 | Accuracy (%) | 71.6 |
| Swallow - Post-trained Japanese - Average | 52.7 | Average Score (%) | 64.2 |
| Swallow - Post-trained Japanese - JamC-QA | 52.1 | Accuracy (%) | 63.4 |
| Swallow - Post-trained English - IFBench | 43.6 | Instruction-Level Strict Accuracy (%) | 62.7 |
| Swallow - Post-trained Japanese - JHumanEval | 90.9 | Pass@1 (%) | 61.2 |
| Swallow - Post-trained English - Average | 69.7 | Average Score (%) | 59.7 |
| Swallow - Post-trained English - GPQA Diamond | 62.1 | Accuracy (%) | 59.7 |
| Swallow - Post-trained English - LiveCodeBench | 53.2 | Pass@1 (%) | 59.7 |
| Swallow - Post-trained English - MATH-500 | 96 | Accuracy (%) | 59.7 |
| Swallow - Post-trained English - MMLU-Pro | 76.1 | Accuracy (%) | 59.7 |
| Swallow - Post-trained Japanese - GPQA | 58.9 | Accuracy (%) | 59.7 |
Interactive version: theaggregate.ai/model?slug=qwen-3-swallow-32b-cpt-v0-2 · How It Works · Data refreshed daily, snapshot 2026-11-08.