← All comparisons
Ministral 3 8B vs EXAONE 4.5 33B (Non-reasoning)
Mistral vs LG AI Research — side-by-side benchmark comparison
| Ministral 3 8B | EXAONE 4.5 33B (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 14.8 | — |
| Coding Index | 10.0 | — |
| Math Index | 31.7 | — |
| Output speed (tok/s) | 100.9 | 0.0 |
| Blended price ($/1M) | $0.15 | $0.00 |
| Time to first token (s) | 0.37s | 0.00s |
| aime | — | — |
| aime 25 | 31.7% | — |
| artificial analysis coding index | 10.00 | — |
| artificial analysis intelligence index | 14.80 | — |
| artificial analysis math index | 31.70 | — |
| gpqa | 47.1% | — |
| hle | 4.3% | — |
| ifbench | 29.1% | — |
| lcr | 24.0% | — |
| livecodebench | 30.3% | — |
| math 500 | — | — |
| mmlu pro | 64.2% | — |
| scicode | 20.8% | — |
| tau2 | 26.6% | — |
| terminalbench hard | 4.5% | — |
Benchmark data from Artificial Analysis.