← All comparisons
EXAONE 4.5 33B (Non-reasoning) vs MiniMax-M2.1
LG AI Research vs MiniMax — side-by-side benchmark comparison
| EXAONE 4.5 33B (Non-reasoning) | MiniMax-M2.1 | |
|---|---|---|
| Intelligence Index | — | 39.4 |
| Coding Index | — | 32.8 |
| Math Index | — | 82.7 |
| Output speed (tok/s) | 0.0 | 188.8 |
| Blended price ($/1M) | $0.00 | $0.53 |
| Time to first token (s) | 0.00s | 2.43s |
| aime | — | — |
| aime 25 | — | 82.7% |
| artificial analysis coding index | — | 32.80 |
| artificial analysis intelligence index | — | 39.40 |
| artificial analysis math index | — | 82.70 |
| gpqa | — | 83.0% |
| hle | — | 22.2% |
| ifbench | — | 69.9% |
| lcr | — | 59.0% |
| livecodebench | — | 81.0% |
| math 500 | — | — |
| mmlu pro | — | 87.5% |
| scicode | — | 40.7% |
| tau2 | — | 85.4% |
| terminalbench hard | — | 28.8% |
Benchmark data from Artificial Analysis.