← All comparisons
Exaone 4.0 1.2B (Reasoning) vs Mi:dm K 2.5 Pro
LG AI Research vs Korea Telecom — side-by-side benchmark comparison
| Exaone 4.0 1.2B (Reasoning) | Mi:dm K 2.5 Pro | |
|---|---|---|
| Intelligence Index | 8.3 | 23.1 |
| Coding Index | 3.1 | 12.6 |
| Math Index | 50.3 | 76.7 |
| Output speed (tok/s) | 0.0 | 0.0 |
| Blended price ($/1M) | $0.00 | $0.00 |
| Time to first token (s) | 0.00s | 0.00s |
| aime | — | — |
| aime 25 | 50.3% | 76.7% |
| artificial analysis coding index | 3.10 | 12.60 |
| artificial analysis intelligence index | 8.30 | 23.10 |
| artificial analysis math index | 50.30 | 76.70 |
| gpqa | 51.5% | 70.1% |
| hle | 5.8% | 7.7% |
| ifbench | 23.0% | 49.3% |
| lcr | 0.0% | 9.0% |
| livecodebench | 51.6% | 65.6% |
| math 500 | — | — |
| mmlu pro | 58.8% | 80.9% |
| scicode | 9.3% | 33.2% |
| tau2 | 16.4% | 86.5% |
| terminalbench hard | 0.0% | 2.3% |
Benchmark data from Artificial Analysis.