GPT-5.6 Luna (Xhigh) vs GPT-6.1 Sol (High)
Which is better for the money: GPT-5.6 Luna (Xhigh) by OpenAI or GPT-6.1 Sol (High) by OpenAI? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-24.
Trade-off
Verdict
Depends on your budget
GPT-6.1 Sol (High) scores 15.6 points higher (50.2 vs 34.6) but costs 2.9× as much to run the benchmark ($521 vs $179; premium vs mid-range cost classes). Pick GPT-6.1 Sol (High) when the extra intelligence is worth the premium, otherwise GPT-5.6 Luna (Xhigh).
| Metric | GPT-5.6 Luna (Xhigh) | GPT-6.1 Sol (High) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 34.6 | 50.2 | +45.1% GPT-6.1 Sol (High) is 45.1% more intelligent |
| Total AA cost (lower is better) | $179.33 | $521.32 | +190.7% GPT-6.1 Sol (High) is 2.9× more expensive |
| End-to-end time (lower is better) | 30.83s | 43.44s | +40.9% GPT-6.1 Sol (High) is 40.9% slower |
| Price per 1M tokens (in / out) | $0.20 / $1.20 | $2.00 / $10.0 | |
| Input modalities | Text, Image | Text, Image |
GPT-6.1 Sol (High) vs GPT-5.6 Luna (Xhigh): 45.1% more intelligence, 190.7% more cost to run the AA benchmark, and 40.9% slower end-to-end.
Today's Pareto frontier
Against the frontier
- GPT-5.6 Luna (Xhigh) is off the frontier: at the same or lower cost, Claude Haiku 5.5 (Xhigh) scores 41.20 for $158.
- GPT-6.1 Sol (High) is on today's frontier: nothing is both smarter and cheaper.
GPT-5.6 Luna (Xhigh)GPT-6.1 Sol (High)Today's Pareto 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-xhigh/gpt-6-1-sol-high · Markdown: /api/v1/compare/gpt-5-6-luna-xhigh/gpt-6-1-sol-high?format=md · llms.txt · agent skill