← All comparisons
EXAONE 4.0 32B (Reasoning) vs Claude 4.1 Opus (Non-reasoning)
LG AI Research vs Anthropic — side-by-side benchmark comparison
| EXAONE 4.0 32B (Reasoning) | Claude 4.1 Opus (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 16.7 | 36.0 |
| Coding Index | 14.0 | — |
| Math Index | 80.0 | — |
| 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 | 84.3% | — |
| aime 25 | 80.0% | — |
| artificial analysis coding index | 14.00 | — |
| artificial analysis intelligence index | 16.70 | 36.00 |
| artificial analysis math index | 80.00 | — |
| gpqa | 73.9% | — |
| hle | 10.5% | — |
| ifbench | 36.3% | — |
| lcr | 14.0% | — |
| livecodebench | 74.7% | — |
| math 500 | 97.7% | — |
| mmlu pro | 81.8% | — |
| scicode | 34.4% | — |
| tau2 | 17.3% | — |
| terminalbench hard | 3.8% | — |
Benchmark data from Artificial Analysis.