← All comparisons
Nova Micro vs Claude 4.5 Sonnet (Reasoning)
Amazon vs Anthropic — side-by-side benchmark comparison
| Nova Micro | Claude 4.5 Sonnet (Reasoning) | |
|---|---|---|
| Intelligence Index | 10.3 | 43.0 |
| Coding Index | 4.1 | 38.6 |
| Math Index | 6.0 | 88.0 |
| Output speed (tok/s) | 324.4 | 55.0 |
| Blended price ($/1M) | $0.06 | $6.56 |
| Time to first token (s) | 0.61s | 7.02s |
| aime | 8.0% | — |
| aime 25 | 6.0% | 88.0% |
| artificial analysis coding index | 4.10 | 38.60 |
| artificial analysis intelligence index | 10.30 | 43.00 |
| artificial analysis math index | 6.00 | 88.00 |
| gpqa | 35.8% | 83.4% |
| hle | 4.7% | 17.3% |
| ifbench | 29.4% | 57.3% |
| lcr | 9.7% | 65.7% |
| livecodebench | 14.0% | 71.4% |
| math 500 | 70.3% | — |
| mmlu pro | 53.1% | 87.5% |
| scicode | 9.4% | 44.7% |
| tau2 | 14.0% | 78.1% |
| terminalbench hard | 1.5% | 35.6% |
Benchmark data from Artificial Analysis.