Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | Qwen3 14B (Non-reasoning) | GPT-3.5 Turbo |
|---|---|---|
| Input ($/M tokens) | $0.35 | $0.5 |
| Output ($/M tokens) | $1.4 | $1.5 |
Data from Artificial Analysis API — 12 benchmarks
Qwen3 14B (Non-reasoning) is cheaper overall. Its blended price (3:1 input/output ratio) is $0.61/M tokens vs $0.75/M for GPT-3.5 Turbo.
Qwen3 14B (Non-reasoning) wins 11 out of 12 benchmarks compared to 1 for GPT-3.5 Turbo. See the detailed benchmark chart above for per-category results.
GPT-3.5 Turbo generates tokens faster at 129 tok/s vs 62 tok/s. However, GPT-3.5 Turbo has lower time-to-first-token (0.80s vs 1.15s).
Choose based on your priorities: Qwen3 14B (Non-reasoning) for lower cost, Qwen3 14B (Non-reasoning) for stronger benchmark performance, and GPT-3.5 Turbo for faster generation. For latency-sensitive apps, check the TTFT comparison above.