← All comparisons
EXAONE 4.5 33B vs Claude 4.1 Opus (Non-reasoning)
LG AI Research vs Anthropic — side-by-side benchmark comparison
| EXAONE 4.5 33B | Claude 4.1 Opus (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 30.2 | 36.0 |
| Coding Index | 23.0 | — |
| Math Index | — | — |
| Output speed (tok/s) | 0.0 | 44.7 |
| Blended price ($/1M) | $0.00 | $32.81 |
| Time to first token (s) | 0.00s | 1.63s |
| aime | — | — |
| aime 25 | — | — |
| artificial analysis coding index | 23.00 | — |
| artificial analysis intelligence index | 30.20 | 36.00 |
| artificial analysis math index | — | — |
| gpqa | 79.4% | — |
| hle | 11.6% | — |
| ifbench | 58.0% | — |
| lcr | 49.3% | — |
| livecodebench | — | — |
| math 500 | — | — |
| mmlu pro | — | — |
| scicode | 28.0% | — |
| tau2 | 78.1% | — |
| terminalbench hard | 20.5% | — |
Benchmark data from Artificial Analysis.