Grok 4.6 (Medium) vs Nemotron 3 Super 120B A12B (Reasoning)
Which is better for the money: Grok 4.6 (Medium) by SpaceXAI or Nemotron 3 Super 120B A12B (Reasoning) by NVIDIA? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-26.
Trade-off
Verdict
Depends on your budget
Grok 4.6 (Medium) scores 30.0 points higher (42.8 vs 12.8) but costs 1.2× as much to run the benchmark ($1557 vs $1319; both premium class). Pick Grok 4.6 (Medium) when the extra intelligence is worth the premium, otherwise Nemotron 3 Super 120B A12B (Reasoning).
| Metric | Grok 4.6 (Medium) | Nemotron 3 Super 120B A12B (Reasoning) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 42.8 | 12.8 | −70.1% Nemotron 3 Super 120B… is 70.1% less intelligent |
| Total AA cost (lower is better) | $1,557.04 | $1,318.62 | −15.3% Nemotron 3 Super 120B… is 15.3% cheaper |
| End-to-end time (lower is better) | 35.16s | 16.68s | −52.6% Nemotron 3 Super 120B… is 52.6% faster |
| Price per 1M tokens (in / out) | $2.00 / $6.00 | $0.30 / $0.90 | |
| Input modalities | Text, Image | Text |
Nemotron 3 Super 120B A12B (Reasoning) vs Grok 4.6 (Medium): 70.1% less intelligence, 15.3% less cost to run the AA benchmark, and 52.6% faster end-to-end.
Today's Pareto frontier
Against the frontier
- Grok 4.6 (Medium) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 51.80 for $1082.
- Nemotron 3 Super 120B A12B (Reasoning) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 51.80 for $1082.
Grok 4.6 (Medium)Nemotron 3 Super 120B A12B (Reasoning)Today's Pareto frontierOpen-weights frontierEvery other model
Matchup
Compare something else
Agents:
Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/grok-4-6-medium/nvidia-nemotron-3-super-120b-a12b · Markdown: /api/v1/compare/grok-4-6-medium/nvidia-nemotron-3-super-120b-a12b?format=md · llms.txt · agent skill