Nova 2.0 Pro Preview (low) vs Nova 2.0 Pro Preview (medium)
Comparing 2 AI models · 5 benchmarks · Amazon
Most Affordable
Am
Nova 2.0 Pro Preview (low)
$1.25/1M
Highest Intelligence
Am
Nova 2.0 Pro Preview (medium)
78.5% GPQA
Best for Coding
Am
Nova 2.0 Pro Preview (medium)
29.4 Coding Index
Price Difference
1.0x
input cost range
Composite Indices
Intelligence, Coding, Math
Standard Benchmarks
Academic and industry benchmarks
Benchmark Winners
5 tests
Am
Nova 2.0 Pro Preview (low)
0
No clear wins
Am
Nova 2.0 Pro Preview (medium)
5
- GPQA
- MMLU Pro
- HLE
- LiveCodeBench
- AIME 2025
| Metric | Am Nova 2.0 Pro Preview (low) | Am Nova 2.0 Pro Preview (medium) |
|---|---|---|
| Pricing Per 1M tokens | ||
| Input Cost | $1.25/1M | $1.25/1M |
| Output Cost | $10.00/1M | $10.00/1M |
| Blended Cost 3:1 input/output ratio | $3.44/1M | $3.44/1M |
| Specifications | ||
| Organization Model creator | Amazon | Amazon |
| Release Date Launch date | Nov 27, 2025 | Nov 27, 2025 |
| Performance & Speed | ||
| Throughput Output speed | 132.8 tok/s | 131.9 tok/s |
| Time to First Token (TTFT) Initial response delay | 12299ms | 19308ms |
| Latency Time to first answer token | 27365ms | 34477ms |
| Composite Indices | ||
| Intelligence Index Overall reasoning capability | 32.0 | 35.3 |
| Coding Index Programming ability | 23.8 | 29.4 |
| Math Index Mathematical reasoning | 63.3 | 89.0 |
| Standard Benchmarks | ||
| GPQA Graduate-level reasoning | 75.1% | 78.5% |
| MMLU Pro Advanced knowledge | 82.2% | 83.0% |
| HLE Hard language evaluation | 5.2% | 8.9% |
| LiveCodeBench Real-world coding tasks | 63.8% | 73.0% |
| MATH 500 Mathematical problems | — | — |
| AIME 2025 Advanced math competition | 63.3% | 89.0% |
| AIME (Original) Math olympiad problems | ||