Qwen-3-Swallow-30B-A3B-CPT-v0.2: benchmark results
Provider: Alibaba.
Aggregate Rating 1537 ± 35, rank #1864 of 10916 rated models, from 35 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Swallow - Post-trained Japanese - WMT20 Ja-En | 22.2 | BLEU | 65.7 |
| Swallow - Post-trained Japanese - JamC-QA | 51.8 | Accuracy (%) | 58.2 |
| Swallow - Post-trained Japanese - MMLU-ProX | 71.5 | Accuracy (%) | 55.2 |
| Swallow - Post-trained Japanese - JHumanEval | 89.5 | Pass@1 (%) | 53 |
| Swallow - Post-trained Japanese - WMT20 En-Ja | 24 | BLEU | 53 |
| Swallow - Post-trained English - MMLU-Pro | 74 | Accuracy (%) | 50.7 |
| Swallow - Post-trained English - IFBench | 39 | Instruction-Level Strict Accuracy (%) | 47.8 |
| Swallow - Post-trained Japanese - Average | 49.8 | Average Score (%) | 47.8 |
| Swallow - Post-trained Japanese - GPQA | 54.2 | Accuracy (%) | 47.8 |
| Swallow - Post-trained English - Average | 65.1 | Average Score (%) | 46.3 |
| Swallow - Post-trained English - LiveCodeBench | 48.1 | Pass@1 (%) | 44.8 |
| Swallow - Post-trained English - AIME | 58.3 | Accuracy (%) | 43.3 |
Interactive version: theaggregate.ai/model?slug=qwen-3-swallow-30b-a3b-cpt-v0-2 · How It Works · Data refreshed daily, snapshot 2026-11-08.