Nemotron 3 Super 120B A12B (Reasoning) vs Beam 1.0
Which is better for the money: Nemotron 3 Super 120B A12B (Reasoning) by NVIDIA or Beam 1.0 by Reflection? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-25.
Clear winner
Verdict
Pick Beam 1.0
Beam 1.0 vs Nemotron 3 Super 120B A12B (Reasoning): 136.7% more intelligence, 75.8% less cost to run the AA benchmark, and 52.6% faster end-to-end.
| Metric | Nemotron 3 Super 120B A12B (Reasoning) | Beam 1.0 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 12.8 | 30.3 | +136.7% Beam 1.0 is 2.4× more intelligent |
| Total AA cost (lower is better) | $1,318.62 | $318.73 | −75.8% Beam 1.0 is 75.8% cheaper |
| End-to-end time (lower is better) | 15.94s | 7.56s | −52.6% Beam 1.0 is 52.6% faster |
| Price per 1M tokens (in / out) | $0.30 / $0.90 | $0.40 / $1.20 | |
| Input modalities | Text | Text |
Today's Pareto frontier
Against the frontier
- 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.
- Beam 1.0 is off the frontier: at the same or lower cost, MiMo-V2.6-Pro scores 46.30 for $207.
Nemotron 3 Super 120B A12B (Reasoning)Beam 1.0Today'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/nvidia-nemotron-3-super-120b-a12b/reflection-beam · Markdown: /api/v1/compare/nvidia-nemotron-3-super-120b-a12b/reflection-beam?format=md · llms.txt · agent skill