← All comparisons
DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning) vs Llama 3.3 Nemotron Super 49B v1 (Reasoning)
Nous Research vs NVIDIA — side-by-side benchmark comparison
| DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning) | Llama 3.3 Nemotron Super 49B v1 (Reasoning) | |
|---|---|---|
| Intelligence Index | 7.6 | 18.5 |
| Coding Index | — | 9.4 |
| Math Index | — | 54.7 |
| Output speed (tok/s) | 0.0 | 0.0 |
| Blended price ($/1M) | $0.00 | $0.00 |
| Time to first token (s) | 0.00s | 0.00s |
| aime | 0.0% | 58.3% |
| aime 25 | — | 54.7% |
| artificial analysis coding index | — | 9.40 |
| artificial analysis intelligence index | 7.60 | 18.50 |
| artificial analysis math index | — | 54.70 |
| gpqa | 27.0% | 64.3% |
| hle | 4.3% | 6.5% |
| ifbench | — | 38.1% |
| lcr | — | 17.0% |
| livecodebench | 8.5% | 27.7% |
| math 500 | 21.8% | 95.9% |
| mmlu pro | 36.5% | 78.5% |
| scicode | 9.1% | 28.2% |
| tau2 | — | 26.9% |
| terminalbench hard | — | 0.0% |
Benchmark data from Artificial Analysis.