← All comparisons
LFM2.5-1.2B-Thinking vs MiMo-V2-Omni
Liquid AI vs Xiaomi — side-by-side benchmark comparison
| LFM2.5-1.2B-Thinking | MiMo-V2-Omni | |
|---|---|---|
| Intelligence Index | 8.1 | 43.4 |
| Coding Index | 1.4 | 35.5 |
| Math Index | — | — |
| Output speed (tok/s) | 0.0 | 96.2 |
| Blended price ($/1M) | $0.00 | $0.00 |
| Time to first token (s) | 0.00s | 2.15s |
| aime | — | — |
| aime 25 | — | — |
| artificial analysis coding index | 1.40 | 35.50 |
| artificial analysis intelligence index | 8.10 | 43.40 |
| artificial analysis math index | — | — |
| gpqa | 33.9% | 82.8% |
| hle | 6.1% | 19.9% |
| ifbench | 41.8% | 53.5% |
| lcr | 0.0% | 66.7% |
| livecodebench | — | — |
| math 500 | — | — |
| mmlu pro | — | — |
| scicode | 4.2% | 36.7% |
| tau2 | 19.6% | 91.2% |
| terminalbench hard | 0.0% | 34.8% |
Benchmark data from Artificial Analysis.