Nemotron 3 Super 120B A12B (Reasoning) vs Qwen3.8 2.4T A95B
Which is better for the money: Nemotron 3 Super 120B A12B (Reasoning) by NVIDIA or Qwen3.8 2.4T A95B by Alibaba? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-27.
Trade-off
Verdict
Depends on your budget
Qwen3.8 2.4T A95B scores 27.1 points higher (39.9 vs 12.8) but costs 2.0× as much to run the benchmark ($2632 vs $1319; flagship vs premium cost classes). Pick Qwen3.8 2.4T A95B when the extra intelligence is worth the premium, otherwise Nemotron 3 Super 120B A12B (Reasoning).
| Metric | Nemotron 3 Super 120B A12B (Reasoning) | Qwen3.8 2.4T A95B | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 12.8 | 39.9 | +211.7% Qwen3.8 2.4T A95B is 3.1× more intelligent |
| Total AA cost (lower is better) | $1,318.62 | $2,632.05 | +99.6% Qwen3.8 2.4T A95B is 99.6% more expensive |
| End-to-end time (lower is better) | 17.13s | 64.93s | +279.0% Qwen3.8 2.4T A95B is 279.0% slower |
| Price per 1M tokens (in / out) | $0.30 / $0.90 | $2.00 / $6.00 | |
| Input modalities | Text | Text |
Qwen3.8 2.4T A95B vs Nemotron 3 Super 120B A12B (Reasoning): 211.7% more intelligence, 99.6% more cost to run the AA benchmark, and 279.0% slower end-to-end.
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.
- Qwen3.8 2.4T A95B is off the frontier: at the same or lower cost, Claude Opus 5.5 (High, Default Fallback) scores 53.60 for $2172.
Nemotron 3 Super 120B A12B (Reasoning)Qwen3.8 2.4T A95BToday'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/qwen3-8-2-4t-a95b · Markdown: /api/v1/compare/nvidia-nemotron-3-super-120b-a12b/qwen3-8-2-4t-a95b?format=md · llms.txt · agent skill