← All comparisons
Claude 4.1 Opus (Reasoning) vs MiMo-V2-Flash (Reasoning)
Anthropic vs Xiaomi — side-by-side benchmark comparison
| Claude 4.1 Opus (Reasoning) | MiMo-V2-Flash (Reasoning) | |
|---|---|---|
| Intelligence Index | 42.0 | 39.2 |
| Coding Index | 36.5 | 31.8 |
| Math Index | 80.3 | 96.3 |
| Output speed (tok/s) | 44.5 | 131.8 |
| Blended price ($/1M) | $32.81 | $0.15 |
| Time to first token (s) | 8.55s | 1.35s |
| aime | — | — |
| aime 25 | 80.3% | 96.3% |
| artificial analysis coding index | 36.50 | 31.80 |
| artificial analysis intelligence index | 42.00 | 39.20 |
| artificial analysis math index | 80.30 | 96.30 |
| gpqa | 80.9% | 84.6% |
| hle | 11.9% | 21.1% |
| ifbench | 55.4% | 64.2% |
| lcr | 66.3% | 63.0% |
| livecodebench | 65.4% | 86.8% |
| math 500 | — | — |
| mmlu pro | 88.0% | 84.3% |
| scicode | 40.9% | 39.4% |
| tau2 | 71.4% | 95.0% |
| terminalbench hard | 34.3% | 28.0% |
Benchmark data from Artificial Analysis.