← All comparisons
Claude 4.1 Opus (Non-reasoning) vs MiMo-V2-Pro
Anthropic vs Xiaomi — side-by-side benchmark comparison
| Claude 4.1 Opus (Non-reasoning) | MiMo-V2-Pro | |
|---|---|---|
| Intelligence Index | 36.0 | 49.2 |
| Coding Index | — | 41.4 |
| Math Index | — | — |
| Output speed (tok/s) | 44.7 | 54.5 |
| Blended price ($/1M) | $32.81 | $1.50 |
| Time to first token (s) | 1.63s | 1.77s |
| aime | — | — |
| aime 25 | — | — |
| artificial analysis coding index | — | 41.40 |
| artificial analysis intelligence index | 36.00 | 49.20 |
| artificial analysis math index | — | — |
| gpqa | — | 87.0% |
| hle | — | 28.3% |
| ifbench | — | 68.8% |
| lcr | — | 60.7% |
| livecodebench | — | — |
| math 500 | — | — |
| mmlu pro | — | — |
| scicode | — | 42.5% |
| tau2 | — | 95.0% |
| terminalbench hard | — | 40.9% |
Benchmark data from Artificial Analysis.