← All comparisons
Claude 4.5 Haiku (Reasoning) vs Llama 3.1 Nemotron Instruct 70B
Anthropic vs NVIDIA — side-by-side benchmark comparison
| Claude 4.5 Haiku (Reasoning) | Llama 3.1 Nemotron Instruct 70B | |
|---|---|---|
| Intelligence Index | 37.1 | 13.4 |
| Coding Index | 32.6 | 10.8 |
| Math Index | 83.7 | 11.0 |
| Output speed (tok/s) | 142.2 | 292.9 |
| Blended price ($/1M) | $2.19 | $1.20 |
| Time to first token (s) | 10.48s | 0.24s |
| aime | — | 24.7% |
| aime 25 | 83.7% | 11.0% |
| artificial analysis coding index | 32.60 | 10.80 |
| artificial analysis intelligence index | 37.10 | 13.40 |
| artificial analysis math index | 83.70 | 11.00 |
| gpqa | 67.2% | 46.5% |
| hle | 9.7% | 4.6% |
| ifbench | 54.3% | 30.7% |
| lcr | 70.3% | 7.0% |
| livecodebench | 61.5% | 16.9% |
| math 500 | — | 73.3% |
| mmlu pro | 76.0% | 69.0% |
| scicode | 43.3% | 23.3% |
| tau2 | 54.7% | 23.1% |
| terminalbench hard | 27.3% | 4.5% |
Benchmark data from Artificial Analysis.