Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | Qwen3.5 397B A17B (Reasoning) | Claude 3.5 Haiku |
|---|---|---|
| Input ($/M tokens) | $0.6 | $0.8 |
| Output ($/M tokens) | $3.6 | $4 |
Data from Artificial Analysis API — 12 benchmarks
Qwen3.5 397B A17B (Reasoning) is cheaper overall. Its blended price (3:1 input/output ratio) is $1.35/M tokens vs $1.60/M for Claude 3.5 Haiku.
Qwen3.5 397B A17B (Reasoning) wins 7 out of 12 benchmarks compared to 3 for Claude 3.5 Haiku. See the detailed benchmark chart above for per-category results.
Qwen3.5 397B A17B (Reasoning) generates tokens faster at 54 tok/s vs 0 tok/s. However, Claude 3.5 Haiku has lower time-to-first-token (0.00s vs 1.39s).
Choose based on your priorities: Qwen3.5 397B A17B (Reasoning) for lower cost, Qwen3.5 397B A17B (Reasoning) for stronger benchmark performance, and Qwen3.5 397B A17B (Reasoning) for faster generation. For latency-sensitive apps, check the TTFT comparison above.