← All comparisons
Nova 2.0 Lite (high) vs Claude 4.1 Opus (Non-reasoning)
Amazon vs Anthropic — side-by-side benchmark comparison
| Nova 2.0 Lite (high) | Claude 4.1 Opus (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 34.5 | 36.0 |
| Coding Index | 23.4 | — |
| Math Index | 94.3 | — |
| Output speed (tok/s) | 165.5 | 44.7 |
| Blended price ($/1M) | $0.85 | $32.81 |
| Time to first token (s) | 10.52s | 1.63s |
| aime | — | — |
| aime 25 | 94.3% | — |
| artificial analysis coding index | 23.40 | — |
| artificial analysis intelligence index | 34.50 | 36.00 |
| artificial analysis math index | 94.30 | — |
| gpqa | 81.1% | — |
| hle | 10.9% | — |
| ifbench | 70.7% | — |
| lcr | 55.3% | — |
| livecodebench | 71.1% | — |
| math 500 | — | — |
| mmlu pro | 81.8% | — |
| scicode | 36.9% | — |
| tau2 | 72.8% | — |
| terminalbench hard | 16.7% | — |
Benchmark data from Artificial Analysis.