← All comparisons
Nova 2.0 Pro Preview (Non-reasoning) vs Claude 4.1 Opus (Reasoning)
Amazon vs Anthropic — side-by-side benchmark comparison
| Nova 2.0 Pro Preview (Non-reasoning) | Claude 4.1 Opus (Reasoning) | |
|---|---|---|
| Intelligence Index | 23.1 | 42.0 |
| Coding Index | 20.5 | 36.5 |
| Math Index | 30.7 | 80.3 |
| Output speed (tok/s) | 154.7 | 44.5 |
| Blended price ($/1M) | $3.44 | $32.81 |
| Time to first token (s) | 0.71s | 8.55s |
| aime | — | — |
| aime 25 | 30.7% | 80.3% |
| artificial analysis coding index | 20.50 | 36.50 |
| artificial analysis intelligence index | 23.10 | 42.00 |
| artificial analysis math index | 30.70 | 80.30 |
| gpqa | 63.6% | 80.9% |
| hle | 4.0% | 11.9% |
| ifbench | 52.0% | 55.4% |
| lcr | 28.3% | 66.3% |
| livecodebench | 47.3% | 65.4% |
| math 500 | — | — |
| mmlu pro | 77.2% | 88.0% |
| scicode | 28.1% | 40.9% |
| tau2 | 71.6% | 71.4% |
| terminalbench hard | 16.7% | 34.3% |
Benchmark data from Artificial Analysis.