← All comparisons
EXAONE 4.0 32B (Non-reasoning) vs Claude 3.5 Sonnet (Oct '24)
LG AI Research vs Anthropic — side-by-side benchmark comparison
| EXAONE 4.0 32B (Non-reasoning) | Claude 3.5 Sonnet (Oct '24) | |
|---|---|---|
| Intelligence Index | 11.7 | 15.9 |
| Coding Index | 9.4 | 30.2 |
| Math Index | 39.3 | — |
| Output speed (tok/s) | 0.0 | 0.0 |
| Blended price ($/1M) | $0.00 | $6.56 |
| Time to first token (s) | 0.00s | 0.00s |
| aime | 47.0% | 15.7% |
| aime 25 | 39.3% | — |
| artificial analysis coding index | 9.40 | 30.20 |
| artificial analysis intelligence index | 11.70 | 15.90 |
| artificial analysis math index | 39.30 | — |
| gpqa | 62.8% | 59.9% |
| hle | 4.9% | 3.9% |
| ifbench | 33.5% | — |
| lcr | 8.0% | — |
| livecodebench | 47.2% | 38.1% |
| math 500 | 93.9% | 77.1% |
| mmlu pro | 76.8% | 77.2% |
| scicode | 25.2% | 36.6% |
| tau2 | 4.1% | — |
| terminalbench hard | 1.5% | — |
Benchmark data from Artificial Analysis.