← All comparisons
Exaone 4.0 1.2B (Non-reasoning) vs Claude 3.5 Sonnet (June '24)
LG AI Research vs Anthropic — side-by-side benchmark comparison
| Exaone 4.0 1.2B (Non-reasoning) | Claude 3.5 Sonnet (June '24) | |
|---|---|---|
| Intelligence Index | 8.1 | 14.2 |
| Coding Index | 2.5 | 26.0 |
| Math Index | 24.0 | — |
| 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 | — | 9.7% |
| aime 25 | 24.0% | — |
| artificial analysis coding index | 2.50 | 26.00 |
| artificial analysis intelligence index | 8.10 | 14.20 |
| artificial analysis math index | 24.00 | — |
| gpqa | 42.4% | 56.0% |
| hle | 5.8% | 3.7% |
| ifbench | 25.3% | — |
| lcr | 0.0% | — |
| livecodebench | 29.3% | — |
| math 500 | — | 69.5% |
| mmlu pro | 50.0% | 75.1% |
| scicode | 7.4% | 31.6% |
| tau2 | 20.5% | — |
| terminalbench hard | 0.0% | — |
Benchmark data from Artificial Analysis.