← All comparisons
Nova 2.0 Pro Preview (medium) vs Claude 3.5 Sonnet (Oct '24)
Amazon vs Anthropic — side-by-side benchmark comparison
| Nova 2.0 Pro Preview (medium) | Claude 3.5 Sonnet (Oct '24) | |
|---|---|---|
| Intelligence Index | 35.7 | 15.9 |
| Coding Index | 30.4 | 30.2 |
| Math Index | 89.0 | — |
| Output speed (tok/s) | 124.9 | 0.0 |
| Blended price ($/1M) | $3.44 | $6.56 |
| Time to first token (s) | 16.70s | 0.00s |
| aime | — | 15.7% |
| aime 25 | 89.0% | — |
| artificial analysis coding index | 30.40 | 30.20 |
| artificial analysis intelligence index | 35.70 | 15.90 |
| artificial analysis math index | 89.00 | — |
| gpqa | 78.5% | 59.9% |
| hle | 8.9% | 3.9% |
| ifbench | 79.0% | — |
| lcr | 54.3% | — |
| livecodebench | 73.0% | 38.1% |
| math 500 | — | 77.1% |
| mmlu pro | 83.0% | 77.2% |
| scicode | 42.7% | 36.6% |
| tau2 | 92.7% | — |
| terminalbench hard | 24.2% | — |
Benchmark data from Artificial Analysis.