← All comparisons
GPT-5.4 nano (medium) vs Exaone 4.0 1.2B (Non-reasoning)
OpenAI vs LG AI Research — side-by-side benchmark comparison
| GPT-5.4 nano (medium) | Exaone 4.0 1.2B (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 38.1 | 8.1 |
| Coding Index | 35.0 | 2.5 |
| Math Index | — | 24.0 |
| Output speed (tok/s) | 152.6 | 0.0 |
| Blended price ($/1M) | $0.46 | $0.00 |
| Time to first token (s) | 2.09s | 0.00s |
| aime | — | — |
| aime 25 | — | 24.0% |
| artificial analysis coding index | 35.00 | 2.50 |
| artificial analysis intelligence index | 38.10 | 8.10 |
| artificial analysis math index | — | 24.00 |
| gpqa | 76.1% | 42.4% |
| hle | 14.7% | 5.8% |
| ifbench | 64.4% | 25.3% |
| lcr | 57.3% | 0.0% |
| livecodebench | — | 29.3% |
| math 500 | — | — |
| mmlu pro | — | 50.0% |
| scicode | 38.4% | 7.4% |
| tau2 | 52.6% | 20.5% |
| terminalbench hard | 33.3% | 0.0% |
Benchmark data from Artificial Analysis.