Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | Qwen3.5 2B (Non-reasoning) | Llama 3.2 Instruct 3B |
|---|---|---|
| Input ($/M tokens) | $0.02 | $0.085 |
| Output ($/M tokens) | $0.1 | $0.085 |
Data from Artificial Analysis API — 12 benchmarks
Qwen3.5 2B (Non-reasoning) is cheaper overall. Its blended price (3:1 input/output ratio) is $0.04/M tokens vs $0.09/M for Llama 3.2 Instruct 3B.
It's a tie — both models win 6 benchmarks each across 12 evaluated categories. See the detailed benchmark chart above for per-category results.
Qwen3.5 2B (Non-reasoning) generates tokens faster at 272 tok/s vs 54 tok/s. However, Llama 3.2 Instruct 3B has lower time-to-first-token (0.35s vs 0.54s).
Choose based on your priorities: Qwen3.5 2B (Non-reasoning) for lower cost, both perform similarly on benchmarks, and Qwen3.5 2B (Non-reasoning) for faster generation. For latency-sensitive apps, check the TTFT comparison above.