← All comparisons
MiMo-V2-Flash (Non-reasoning) vs Claude 3.5 Sonnet (June '24)
Xiaomi vs Anthropic — side-by-side benchmark comparison
| MiMo-V2-Flash (Non-reasoning) | Claude 3.5 Sonnet (June '24) | |
|---|---|---|
| Intelligence Index | 30.3 | 14.2 |
| Coding Index | 25.8 | 26.0 |
| Math Index | 67.7 | — |
| Output speed (tok/s) | 142.6 | 0.0 |
| Blended price ($/1M) | $0.15 | $6.56 |
| Time to first token (s) | 1.19s | 0.00s |
| aime | — | 9.7% |
| aime 25 | 67.7% | — |
| artificial analysis coding index | 25.80 | 26.00 |
| artificial analysis intelligence index | 30.30 | 14.20 |
| artificial analysis math index | 67.70 | — |
| gpqa | 65.6% | 56.0% |
| hle | 8.0% | 3.7% |
| ifbench | 39.9% | — |
| lcr | 31.3% | — |
| livecodebench | 40.2% | — |
| math 500 | — | 69.5% |
| mmlu pro | 74.4% | 75.1% |
| scicode | 25.9% | 31.6% |
| tau2 | 83.9% | — |
| terminalbench hard | 25.8% | — |
Benchmark data from Artificial Analysis.