GPT-6 Luna (Xhigh) vs Granite 4.2 30B
Which is better for the money: GPT-6 Luna (Xhigh) by OpenAI or Granite 4.2 30B by IBM? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-26.
Clear winner
Verdict
Pick GPT-6 Luna (Xhigh)
Granite 4.2 30B vs GPT-6 Luna (Xhigh): 63.3% less intelligence, 65.9% more cost to run the AA benchmark, and 130.2% slower end-to-end.
| Metric | GPT-6 Luna (Xhigh) | Granite 4.2 30B | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 34.6 | 12.7 | −63.3% Granite 4.2 30B is 63.3% less intelligent |
| Total AA cost (lower is better) | $66.81 | $110.83 | +65.9% Granite 4.2 30B is 65.9% more expensive |
| End-to-end time (lower is better) | 28.32s | 65.19s | +130.2% Granite 4.2 30B is 130.2% slower |
| Price per 1M tokens (in / out) | $0.10 / $0.50 | $0.16 / $0.65 | |
| Input modalities | Text, Image | Text |
Today's Pareto frontier
Against the frontier
- GPT-6 Luna (Xhigh) is on today's frontier: nothing is both smarter and cheaper.
- Granite 4.2 30B is off the frontier: at the same or lower cost, MiMo-V2.6-Flash scores 37.90 for $110.
GPT-6 Luna (Xhigh)Granite 4.2 30BToday'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-6-luna-xhigh/granite-4-2-30b · Markdown: /api/v1/compare/gpt-6-luna-xhigh/granite-4-2-30b?format=md · llms.txt · agent skill