Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | NVIDIA Nemotron 3 Super 120B A12B (Reasoning) | Mercury 2 |
|---|---|---|
| Input ($/M tokens) | $0.3 | $0.25 |
| Output ($/M tokens) | $0.75 | $0.75 |
Data from Artificial Analysis API — 12 benchmarks
Mercury 2 is cheaper overall. Its blended price (3:1 input/output ratio) is $0.38/M tokens vs $0.41/M for NVIDIA Nemotron 3 Super 120B A12B (Reasoning).
NVIDIA Nemotron 3 Super 120B A12B (Reasoning) wins 6 out of 12 benchmarks compared to 1 for Mercury 2. See the detailed benchmark chart above for per-category results.
Mercury 2 generates tokens faster at 907 tok/s vs 370 tok/s. NVIDIA Nemotron 3 Super 120B A12B (Reasoning) also has lower time-to-first-token (0.55s vs 3.76s).
Choose based on your priorities: Mercury 2 for lower cost, NVIDIA Nemotron 3 Super 120B A12B (Reasoning) for stronger benchmark performance, and Mercury 2 for faster generation. For latency-sensitive apps, check the TTFT comparison above.