Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | Qwen3 32B (Non-reasoning) | Apertus 70B Instruct |
|---|---|---|
| Input ($/M tokens) | $0.7 | $0.82 |
| Output ($/M tokens) | $2.8 | $2.92 |
Data from Artificial Analysis API — 12 benchmarks
Qwen3 32B (Non-reasoning) is cheaper overall. Its blended price (3:1 input/output ratio) is $1.23/M tokens vs $1.34/M for Apertus 70B Instruct.
Qwen3 32B (Non-reasoning) wins 9 out of 12 benchmarks compared to 3 for Apertus 70B Instruct. See the detailed benchmark chart above for per-category results.
Qwen3 32B (Non-reasoning) generates tokens faster at 104 tok/s vs 64 tok/s. Qwen3 32B (Non-reasoning) also has lower time-to-first-token (0.97s vs 1.68s).
Choose based on your priorities: Qwen3 32B (Non-reasoning) for lower cost, Qwen3 32B (Non-reasoning) for stronger benchmark performance, and Qwen3 32B (Non-reasoning) for faster generation. For latency-sensitive apps, check the TTFT comparison above.