Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | Qwen3 30B A3B (Reasoning) | Nova 2.0 Lite (Non-reasoning) |
|---|---|---|
| Input ($/M tokens) | $0.2 | $0.3 |
| Output ($/M tokens) | $2.4 | $2.5 |
Data from Artificial Analysis API — 12 benchmarks
Qwen3 30B A3B (Reasoning) is cheaper overall. Its blended price (3:1 input/output ratio) is $0.75/M tokens vs $0.85/M for Nova 2.0 Lite (Non-reasoning).
Qwen3 30B A3B (Reasoning) wins 9 out of 12 benchmarks compared to 3 for Nova 2.0 Lite (Non-reasoning). See the detailed benchmark chart above for per-category results.
Nova 2.0 Lite (Non-reasoning) generates tokens faster at 197 tok/s vs 68 tok/s. However, Nova 2.0 Lite (Non-reasoning) has lower time-to-first-token (0.55s vs 1.04s).
Choose based on your priorities: Qwen3 30B A3B (Reasoning) for lower cost, Qwen3 30B A3B (Reasoning) for stronger benchmark performance, and Nova 2.0 Lite (Non-reasoning) for faster generation. For latency-sensitive apps, check the TTFT comparison above.