Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | GPT-5.6 Luna (xhigh) | Qwen3 Next 80B A3B (Reasoning) |
|---|---|---|
| Input ($/M tokens) | $1 | $0.5 |
| Output ($/M tokens) | $6 | $6 |
Data from Artificial Analysis API — 12 benchmarks
Qwen3 Next 80B A3B (Reasoning) is cheaper overall. Its blended price (3:1 input/output ratio) is $1.88/M tokens vs $2.25/M for GPT-5.6 Luna (xhigh).
Qwen3 Next 80B A3B (Reasoning) wins 6 out of 12 benchmarks compared to 5 for GPT-5.6 Luna (xhigh). See the detailed benchmark chart above for per-category results.
GPT-5.6 Luna (xhigh) generates tokens faster at 200 tok/s vs 168 tok/s. However, Qwen3 Next 80B A3B (Reasoning) has lower time-to-first-token (1.23s vs 6.09s).
Choose based on your priorities: Qwen3 Next 80B A3B (Reasoning) for lower cost, Qwen3 Next 80B A3B (Reasoning) for stronger benchmark performance, and GPT-5.6 Luna (xhigh) for faster generation. For latency-sensitive apps, check the TTFT comparison above.