GPT-5.6 Luna (Xhigh) vs MiMo-V2.5
Which is better for the money: GPT-5.6 Luna (Xhigh) by OpenAI or MiMo-V2.5 by Xiaomi? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-26.
Trade-off
Verdict
Depends on your budget
GPT-5.6 Luna (Xhigh) scores 12.8 points higher (34.6 vs 21.8) but costs 2.7× as much to run the benchmark ($179 vs $66.1; both mid-range class). Pick GPT-5.6 Luna (Xhigh) when the extra intelligence is worth the premium, otherwise MiMo-V2.5.
| Metric | GPT-5.6 Luna (Xhigh) | MiMo-V2.5 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 34.6 | 21.8 | −37.0% MiMo-V2.5 is 37.0% less intelligent |
| Total AA cost (lower is better) | $179.33 | $66.09 | −63.1% MiMo-V2.5 is 63.1% cheaper |
| End-to-end time (lower is better) | 45.80s | 67.11s | +46.5% MiMo-V2.5 is 46.5% slower |
| Price per 1M tokens (in / out) | $0.20 / $1.20 | $0.13 / $0.27 | |
| Input modalities | Text, Image | Text, Image |
MiMo-V2.5 vs GPT-5.6 Luna (Xhigh): 37.0% less intelligence, 63.1% less cost to run the AA benchmark, and 46.5% 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, GPT-6.1 Terra (Medium) scores 41.30 for $175.
- MiMo-V2.5 is off the frontier: at the same or lower cost, Claude Haiku 5.5 (Medium) scores 34.50 for $56.4.
GPT-5.6 Luna (Xhigh)MiMo-V2.5Today'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-xhigh/mimo-v2-5-0424 · Markdown: /api/v1/compare/gpt-5-6-luna-xhigh/mimo-v2-5-0424?format=md · llms.txt · agent skill