← All comparisons
EXAONE 4.0 32B (Non-reasoning) vs Claude 4.1 Opus (Reasoning)
LG AI Research vs Anthropic — side-by-side benchmark comparison
| EXAONE 4.0 32B (Non-reasoning) | Claude 4.1 Opus (Reasoning) | |
|---|---|---|
| Intelligence Index | 11.7 | 42.0 |
| Coding Index | 9.4 | 36.5 |
| Math Index | 39.3 | 80.3 |
| Output speed (tok/s) | 0.0 | 44.5 |
| Blended price ($/1M) | $0.00 | $32.81 |
| Time to first token (s) | 0.00s | 8.55s |
| aime | 47.0% | — |
| aime 25 | 39.3% | 80.3% |
| artificial analysis coding index | 9.40 | 36.50 |
| artificial analysis intelligence index | 11.70 | 42.00 |
| artificial analysis math index | 39.30 | 80.30 |
| gpqa | 62.8% | 80.9% |
| hle | 4.9% | 11.9% |
| ifbench | 33.5% | 55.4% |
| lcr | 8.0% | 66.3% |
| livecodebench | 47.2% | 65.4% |
| math 500 | 93.9% | — |
| mmlu pro | 76.8% | 88.0% |
| scicode | 25.2% | 40.9% |
| tau2 | 4.1% | 71.4% |
| terminalbench hard | 1.5% | 34.3% |
Benchmark data from Artificial Analysis.