← All comparisons
Llama Nemotron Super 49B v1.5 (Non-reasoning) vs Claude 3.5 Sonnet (June '24)
NVIDIA vs Anthropic — side-by-side benchmark comparison
| Llama Nemotron Super 49B v1.5 (Non-reasoning) | Claude 3.5 Sonnet (June '24) | |
|---|---|---|
| Intelligence Index | 14.6 | 14.2 |
| Coding Index | 10.5 | 26.0 |
| Math Index | 8.0 | — |
| Output speed (tok/s) | 48.9 | 0.0 |
| Blended price ($/1M) | $0.17 | $6.56 |
| Time to first token (s) | 0.28s | 0.00s |
| aime | 13.7% | 9.7% |
| aime 25 | 8.0% | — |
| artificial analysis coding index | 10.50 | 26.00 |
| artificial analysis intelligence index | 14.60 | 14.20 |
| artificial analysis math index | 8.00 | — |
| gpqa | 48.1% | 56.0% |
| hle | 4.3% | 3.7% |
| ifbench | 32.9% | — |
| lcr | 22.0% | — |
| livecodebench | 29.0% | — |
| math 500 | 77.0% | 69.5% |
| mmlu pro | 69.2% | 75.1% |
| scicode | 23.8% | 31.6% |
| tau2 | 25.1% | — |
| terminalbench hard | 3.8% | — |
Benchmark data from Artificial Analysis.