← All comparisons
GPT-4.1 nano vs Llama 3.3 Nemotron Super 49B v1 (Reasoning)
OpenAI vs NVIDIA — side-by-side benchmark comparison
| GPT-4.1 nano | Llama 3.3 Nemotron Super 49B v1 (Reasoning) | |
|---|---|---|
| Intelligence Index | 13.0 | 18.5 |
| Coding Index | 11.2 | 9.4 |
| Math Index | 24.0 | 54.7 |
| Output speed (tok/s) | 178.9 | 0.0 |
| Blended price ($/1M) | $0.17 | $0.00 |
| Time to first token (s) | 0.40s | 0.00s |
| aime | 23.7% | 58.3% |
| aime 25 | 24.0% | 54.7% |
| artificial analysis coding index | 11.20 | 9.40 |
| artificial analysis intelligence index | 13.00 | 18.50 |
| artificial analysis math index | 24.00 | 54.70 |
| gpqa | 51.2% | 64.3% |
| hle | 3.9% | 6.5% |
| ifbench | 32.0% | 38.1% |
| lcr | 17.0% | 17.0% |
| livecodebench | 32.6% | 27.7% |
| math 500 | 84.8% | 95.9% |
| mmlu pro | 65.7% | 78.5% |
| scicode | 25.9% | 28.2% |
| tau2 | 17.3% | 26.9% |
| terminalbench hard | 3.8% | 0.0% |
Benchmark data from Artificial Analysis.