← All comparisons
Granite 4.0 H 350M vs Llama 3.3 Nemotron Super 49B v1 (Non-reasoning)
IBM vs NVIDIA — side-by-side benchmark comparison
| Granite 4.0 H 350M | Llama 3.3 Nemotron Super 49B v1 (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 5.4 | 14.3 |
| Coding Index | 0.6 | 7.6 |
| Math Index | 1.3 | 7.7 |
| 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 | — | 19.3% |
| aime 25 | 1.3% | 7.7% |
| artificial analysis coding index | 60.0% | 7.60 |
| artificial analysis intelligence index | 5.40 | 14.30 |
| artificial analysis math index | 1.30 | 7.70 |
| gpqa | 25.7% | 51.7% |
| hle | 6.4% | 3.5% |
| ifbench | 17.6% | 39.5% |
| lcr | 0.0% | 11.3% |
| livecodebench | 1.9% | 28.0% |
| math 500 | — | 77.5% |
| mmlu pro | 12.7% | 69.8% |
| scicode | 1.7% | 22.9% |
| tau2 | 14.6% | — |
| terminalbench hard | 0.0% | 0.0% |
Benchmark data from Artificial Analysis.