Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | GLM-4.7 (Non-reasoning) | Qwen3 Coder 30B A3B Instruct |
|---|---|---|
| Input ($/M tokens) | $0.55 | $0.45 |
| Output ($/M tokens) | $2.15 | $2.25 |
Data from Artificial Analysis API — 12 benchmarks
Qwen3 Coder 30B A3B Instruct is cheaper overall. Its blended price (3:1 input/output ratio) is $0.90/M tokens vs $0.94/M for GLM-4.7 (Non-reasoning).
GLM-4.7 (Non-reasoning) wins 11 out of 12 benchmarks compared to 1 for Qwen3 Coder 30B A3B Instruct. See the detailed benchmark chart above for per-category results.
GLM-4.7 (Non-reasoning) generates tokens faster at 77 tok/s vs 26 tok/s. GLM-4.7 (Non-reasoning) also has lower time-to-first-token (0.66s vs 1.47s).
Choose based on your priorities: Qwen3 Coder 30B A3B Instruct for lower cost, GLM-4.7 (Non-reasoning) for stronger benchmark performance, and GLM-4.7 (Non-reasoning) for faster generation. For latency-sensitive apps, check the TTFT comparison above.