← All comparisons
Mi:dm K 2.5 Pro vs Claude 3.5 Sonnet (June '24)
Korea Telecom vs Anthropic — side-by-side benchmark comparison
| Mi:dm K 2.5 Pro | Claude 3.5 Sonnet (June '24) | |
|---|---|---|
| Intelligence Index | 23.1 | 14.2 |
| Coding Index | 12.6 | 26.0 |
| Math Index | 76.7 | — |
| Output speed (tok/s) | 0.0 | 0.0 |
| Blended price ($/1M) | $0.00 | $6.56 |
| Time to first token (s) | 0.00s | 0.00s |
| aime | — | 9.7% |
| aime 25 | 76.7% | — |
| artificial analysis coding index | 12.60 | 26.00 |
| artificial analysis intelligence index | 23.10 | 14.20 |
| artificial analysis math index | 76.70 | — |
| gpqa | 70.1% | 56.0% |
| hle | 7.7% | 3.7% |
| ifbench | 49.3% | — |
| lcr | 9.0% | — |
| livecodebench | 65.6% | — |
| math 500 | — | 69.5% |
| mmlu pro | 80.9% | 75.1% |
| scicode | 33.2% | 31.6% |
| tau2 | 86.5% | — |
| terminalbench hard | 2.3% | — |
Benchmark data from Artificial Analysis.