← All comparisons
MiMo-V2-Omni vs Claude 4.1 Opus (Non-reasoning)
Xiaomi vs Anthropic — side-by-side benchmark comparison
| MiMo-V2-Omni | Claude 4.1 Opus (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 43.4 | 36.0 |
| Coding Index | 35.5 | — |
| Math Index | — | — |
| Output speed (tok/s) | 96.2 | 44.7 |
| Blended price ($/1M) | $0.00 | $32.81 |
| Time to first token (s) | 2.15s | 1.63s |
| aime | — | — |
| aime 25 | — | — |
| artificial analysis coding index | 35.50 | — |
| artificial analysis intelligence index | 43.40 | 36.00 |
| artificial analysis math index | — | — |
| gpqa | 82.8% | — |
| hle | 19.9% | — |
| ifbench | 53.5% | — |
| lcr | 66.7% | — |
| livecodebench | — | — |
| math 500 | — | — |
| mmlu pro | — | — |
| scicode | 36.7% | — |
| tau2 | 91.2% | — |
| terminalbench hard | 34.8% | — |
Benchmark data from Artificial Analysis.