← All comparisons
Nova 2.0 Pro Preview (low) vs Claude 4.1 Opus (Reasoning)
Amazon vs Anthropic — side-by-side benchmark comparison
| Nova 2.0 Pro Preview (low) | Claude 4.1 Opus (Reasoning) | |
|---|---|---|
| Intelligence Index | 31.9 | 42.0 |
| Coding Index | 24.5 | 36.5 |
| Math Index | 63.3 | 80.3 |
| Output speed (tok/s) | 129.1 | 44.5 |
| Blended price ($/1M) | $3.44 | $32.81 |
| Time to first token (s) | 3.95s | 8.55s |
| aime | — | — |
| aime 25 | 63.3% | 80.3% |
| artificial analysis coding index | 24.50 | 36.50 |
| artificial analysis intelligence index | 31.90 | 42.00 |
| artificial analysis math index | 63.30 | 80.30 |
| gpqa | 75.1% | 80.9% |
| hle | 5.2% | 11.9% |
| ifbench | 79.6% | 55.4% |
| lcr | 61.7% | 66.3% |
| livecodebench | 63.8% | 65.4% |
| math 500 | — | — |
| mmlu pro | 82.2% | 88.0% |
| scicode | 38.7% | 40.9% |
| tau2 | 90.6% | 71.4% |
| terminalbench hard | 17.4% | 34.3% |
Benchmark data from Artificial Analysis.