Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | Qwen2.5 Instruct 72B | Grok 3 mini Reasoning (high) |
|---|---|---|
| Input ($/M tokens) | $0.475 | $0.3 |
| Output ($/M tokens) | $0.495 | $0.5 |
Data from Artificial Analysis API — 12 benchmarks
Grok 3 mini Reasoning (high) is cheaper overall. Its blended price (3:1 input/output ratio) is $0.35/M tokens vs $0.48/M for Qwen2.5 Instruct 72B.
Grok 3 mini Reasoning (high) wins 11 out of 12 benchmarks compared to 0 for Qwen2.5 Instruct 72B. See the detailed benchmark chart above for per-category results.
Grok 3 mini Reasoning (high) generates tokens faster at 43 tok/s vs 0 tok/s. Qwen2.5 Instruct 72B also has lower time-to-first-token (0.00s vs 0.69s).
Choose based on your priorities: Grok 3 mini Reasoning (high) for lower cost, Grok 3 mini Reasoning (high) for stronger benchmark performance, and Grok 3 mini Reasoning (high) for faster generation. For latency-sensitive apps, check the TTFT comparison above.