Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | GLM-5.2 (Non-reasoning) | GPT-5.6 Luna (max) |
|---|---|---|
| Input ($/M tokens) | $2.09 | $1 |
| Output ($/M tokens) | $6.38 | $6 |
Data from Artificial Analysis API — 12 benchmarks
GPT-5.6 Luna (max) is cheaper overall. Its blended price (3:1 input/output ratio) is $2.25/M tokens vs $3.16/M for GLM-5.2 (Non-reasoning).
GPT-5.6 Luna (max) wins 5 out of 12 benchmarks compared to 0 for GLM-5.2 (Non-reasoning). See the detailed benchmark chart above for per-category results.
GPT-5.6 Luna (max) generates tokens faster at 253 tok/s vs 121 tok/s. GLM-5.2 (Non-reasoning) also has lower time-to-first-token (1.09s vs 62.09s).
Choose based on your priorities: GPT-5.6 Luna (max) for lower cost, GPT-5.6 Luna (max) for stronger benchmark performance, and GPT-5.6 Luna (max) for faster generation. For latency-sensitive apps, check the TTFT comparison above.