GPT-5.6 Luna (Non-reasoning) vs Nemotron 3 Super 120B A12B (Reasoning)
Which is better for the money: GPT-5.6 Luna (Non-reasoning) by OpenAI or Nemotron 3 Super 120B A12B (Reasoning) by NVIDIA? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-27.
Clear winner
Verdict
Pick GPT-5.6 Luna (Non-reasoning)
Nemotron 3 Super 120B A12B (Reasoning) vs GPT-5.6 Luna (Non-reasoning): 17.4% less intelligence, 5640.6% more cost to run the AA benchmark, and 233.3% slower end-to-end.
| Metric | GPT-5.6 Luna (Non-reasoning) | Nemotron 3 Super 120B A12B (Reasoning) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 15.5 | 12.8 | −17.4% Nemotron 3 Super 120B… is 17.4% less intelligent |
| Total AA cost (lower is better) | $22.97 | $1,318.62 | +5640.6% Nemotron 3 Super 120B… is 57× more expensive |
| End-to-end time (lower is better) | 5.14s | 17.13s | +233.3% Nemotron 3 Super 120B… is 233.3% slower |
| Price per 1M tokens (in / out) | $0.20 / $1.20 | $0.30 / $0.90 | |
| Input modalities | Text, Image | Text |
Today's Pareto frontier
Against the frontier
- GPT-5.6 Luna (Non-reasoning) is off the frontier: at the same or lower cost, GPT-6 Luna (Low) scores 21.50 for $10.6.
- 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.
GPT-5.6 Luna (Non-reasoning)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/gpt-5-6-luna-non-reasoning/nvidia-nemotron-3-super-120b-a12b · Markdown: /api/v1/compare/gpt-5-6-luna-non-reasoning/nvidia-nemotron-3-super-120b-a12b?format=md · llms.txt · agent skill