← All comparisons
MiMo-V2.5-Pro (Non-reasoning) vs Qwen3 Omni 30B A3B (Reasoning)
Xiaomi vs Alibaba — side-by-side benchmark comparison
| MiMo-V2.5-Pro (Non-reasoning) | Qwen3 Omni 30B A3B (Reasoning) | |
|---|---|---|
| Intelligence Index | 35.6 | 15.6 |
| Coding Index | 36.8 | 12.7 |
| Math Index | — | 74.0 |
| Output speed (tok/s) | 53.5 | 100.1 |
| Blended price ($/1M) | $1.35 | $0.43 |
| Time to first token (s) | 2.13s | 0.97s |
| aime | — | — |
| aime 25 | — | 74.0% |
| artificial analysis coding index | 36.80 | 12.70 |
| artificial analysis intelligence index | 35.60 | 15.60 |
| artificial analysis math index | — | 74.00 |
| gpqa | 76.2% | 72.6% |
| hle | 13.3% | 7.3% |
| ifbench | 42.7% | 43.4% |
| lcr | 35.0% | 0.0% |
| livecodebench | — | 67.9% |
| math 500 | — | — |
| mmlu pro | — | 79.2% |
| scicode | 39.1% | 30.6% |
| tau2 | 72.5% | 21.3% |
| terminalbench hard | 35.6% | 3.8% |
Benchmark data from Artificial Analysis.