Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | Qwen3 30B A3B 2507 (Reasoning) | MiMo-V2.5 |
|---|---|---|
| Input ($/M tokens) | $0.28 | $0.36 |
| Output ($/M tokens) | $1.85 | $1.8 |
Data from Artificial Analysis API — 12 benchmarks
Qwen3 30B A3B 2507 (Reasoning) is cheaper overall. Its blended price (3:1 input/output ratio) is $0.67/M tokens vs $0.72/M for MiMo-V2.5.
MiMo-V2.5 wins 7 out of 12 benchmarks compared to 5 for Qwen3 30B A3B 2507 (Reasoning). See the detailed benchmark chart above for per-category results.
Qwen3 30B A3B 2507 (Reasoning) generates tokens faster at 144 tok/s vs 87 tok/s. Qwen3 30B A3B 2507 (Reasoning) also has lower time-to-first-token (1.00s vs 1.99s).
Choose based on your priorities: Qwen3 30B A3B 2507 (Reasoning) for lower cost, MiMo-V2.5 for stronger benchmark performance, and Qwen3 30B A3B 2507 (Reasoning) for faster generation. For latency-sensitive apps, check the TTFT comparison above.