Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | Nemotron 3 Super 120B A12B (Reasoning) | Granite 4.2 30B |
|---|---|---|
| Input ($/M tokens) | $0.19 | $0.16 |
| Output ($/M tokens) | $0.65 | $0.65 |
Verdict. Nemotron 3 Super 120B A12B (Reasoning) and Granite 4.2 30B split the benchmark comparison evenly at 1–1. The tiebreaker here is price, speed, and what you actually run them on.
Pricing. Both models sit in the budget bracket for output-token pricing. At 1.0× the per-million-token cost, Granite 4.2 30B is meaningfully cheaper if your traffic is output-heavy (long completions, document generation, agent loops). Granite 4.2 30B makes more sense when output volume is low and absolute reasoning quality justifies the premium.
Strengths. Nemotron 3 Super 120B A12B (Reasoning) is strongest on Coding Index (37.7), Intelligence Index (13.6). Granite 4.2 30B leads on Coding Index (29.9), Intelligence Index (14.8).
Speed. On throughput, Nemotron 3 Super 120B A12B (Reasoning) generates tokens at 173 tok/s versus 77 tok/s — about 55% faster. On time-to-first-token, Granite 4.2 30B responds in 810ms vs 2390ms, which matters most for chat-style UIs.
Provider. NVIDIA and IBM sell to overlapping but distinct developer audiences: NVIDIA tends to ship frontier reasoning models with premium positioning, while IBM often prices more aggressively. Your existing vendor relationships, billing, and SLA preferences may matter as much as the raw numbers above.
Workload cost. Workload scenarios (per million requests at 30M input + 15M output tokens): Nemotron 3 Super 120B A12B (Reasoning) costs $15.45 ($185/year); Granite 4.2 30B costs $14.55 ($175/year). At a smaller 5M-input/2M-output scale (single-developer tool or prototype): Nemotron 3 Super 120B A12B (Reasoning) ≈ $2.25/run, Granite 4.2 30B ≈ $2.10/run. At agent/realtime scale (200M input / 100M output per million requests): Nemotron 3 Super 120B A12B (Reasoning) ≈ $103/run, Granite 4.2 30B ≈ $97/run. Granite 4.2 30B becomes more attractive at higher volume — the absolute per-token pricing difference compounds when you ship at scale.
Recommendation. Both models have legitimate use cases — the right answer depends on whether you are optimizing for benchmark ceiling, latency, or unit cost. Start with the cheaper / faster model, evaluate against your specific task, and only switch if the upgrade shows a meaningful lift.
Head-to-head deltas
Data from Artificial Analysis API — 12 benchmarks
Granite 4.2 30B is cheaper overall. Its blended price (3:1 input/output ratio) is $0.28/M tokens vs $0.30/M for Nemotron 3 Super 120B A12B (Reasoning).
It's a tie — both models win 1 benchmarks each across 12 evaluated categories. See the detailed benchmark chart above for per-category results.
Nemotron 3 Super 120B A12B (Reasoning) generates tokens faster at 173 tok/s vs 77 tok/s. However, Granite 4.2 30B has lower time-to-first-token (0.81s vs 2.39s).
Choose based on your priorities: Granite 4.2 30B for lower cost, both perform similarly on benchmarks, and Nemotron 3 Super 120B A12B (Reasoning) for faster generation. For latency-sensitive apps, check the TTFT comparison above.