← All comparisons
Llama Nemotron Super 49B v1.5 (Reasoning) vs Claude 4.1 Opus (Reasoning)
NVIDIA vs Anthropic — side-by-side benchmark comparison
| Llama Nemotron Super 49B v1.5 (Reasoning) | Claude 4.1 Opus (Reasoning) | |
|---|---|---|
| Intelligence Index | 18.7 | 42.0 |
| Coding Index | 15.1 | 36.5 |
| Math Index | 76.7 | 80.3 |
| Output speed (tok/s) | 48.1 | 44.5 |
| Blended price ($/1M) | $0.17 | $32.81 |
| Time to first token (s) | 0.30s | 8.55s |
| aime | 86.0% | — |
| aime 25 | 76.7% | 80.3% |
| artificial analysis coding index | 15.10 | 36.50 |
| artificial analysis intelligence index | 18.70 | 42.00 |
| artificial analysis math index | 76.70 | 80.30 |
| gpqa | 74.8% | 80.9% |
| hle | 6.8% | 11.9% |
| ifbench | 37.0% | 55.4% |
| lcr | 34.0% | 66.3% |
| livecodebench | 73.7% | 65.4% |
| math 500 | 98.3% | — |
| mmlu pro | 81.4% | 88.0% |
| scicode | 34.8% | 40.9% |
| tau2 | 28.1% | 71.4% |
| terminalbench hard | 5.3% | 34.3% |
Benchmark data from Artificial Analysis.