← All comparisons
Nova Premier vs Claude 3.5 Sonnet (Oct '24)
Amazon vs Anthropic — side-by-side benchmark comparison
| Nova Premier | Claude 3.5 Sonnet (Oct '24) | |
|---|---|---|
| Intelligence Index | 19.0 | 15.9 |
| Coding Index | 13.8 | 30.2 |
| Math Index | 17.3 | — |
| Output speed (tok/s) | 70.2 | 0.0 |
| Blended price ($/1M) | $5.00 | $6.56 |
| Time to first token (s) | 1.12s | 0.00s |
| aime | 17.0% | 15.7% |
| aime 25 | 17.3% | — |
| artificial analysis coding index | 13.80 | 30.20 |
| artificial analysis intelligence index | 19.00 | 15.90 |
| artificial analysis math index | 17.30 | — |
| gpqa | 56.9% | 59.9% |
| hle | 4.7% | 3.9% |
| ifbench | 36.2% | — |
| lcr | 30.0% | — |
| livecodebench | 31.7% | 38.1% |
| math 500 | 83.9% | 77.1% |
| mmlu pro | 73.3% | 77.2% |
| scicode | 27.9% | 36.6% |
| tau2 | 38.3% | — |
| terminalbench hard | 6.8% | — |
Benchmark data from Artificial Analysis.