GPT-5.6 Luna (Non-reasoning) vs GPT-6.1 Terra (High)
Which is better for the money: GPT-5.6 Luna (Non-reasoning) by OpenAI or GPT-6.1 Terra (High) by OpenAI? 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
GPT-6.1 Terra (High) scores 28.4 points higher (43.9 vs 15.5) but costs 10× as much to run the benchmark ($239 vs $23.0; mid-range vs budget cost classes). They are not alternatives at one budget: pick GPT-6.1 Terra (High) when you need intelligence above 15.5, and GPT-5.6 Luna (Non-reasoning) when 15.5 is enough.
| Metric | GPT-5.6 Luna (Non-reasoning) | GPT-6.1 Terra (High) | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 15.5 | 43.9 | +183.2% GPT-6.1 Terra (High) is 2.8× more intelligent |
| Total AA cost (lower is better) | $22.97 | $238.53 | +938.4% GPT-6.1 Terra (High) is 10× more expensive |
| End-to-end time (lower is better) | 5.06s | 11.16s | +120.6% GPT-6.1 Terra (High) is 120.6% slower |
| Price per 1M tokens (in / out) | $0.20 / $1.20 | $1.00 / $5.00 | |
| Input modalities | Text, Image | Text, Image |
GPT-6.1 Terra (High) vs GPT-5.6 Luna (Non-reasoning): 183.2% more intelligence, 938.4% more cost to run the AA benchmark, and 120.6% slower end-to-end.
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.
- GPT-6.1 Terra (High) is off the frontier: at the same or lower cost, MiMo-V2.6-Pro scores 46.30 for $207.
GPT-5.6 Luna (Non-reasoning)GPT-6.1 Terra (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-non-reasoning/gpt-6-1-terra-high · Markdown: /api/v1/compare/gpt-5-6-luna-non-reasoning/gpt-6-1-terra-high?format=md · llms.txt · agent skill