GPT-6.1 Terra (Low) vs MiMo-V2.6-Pro
Which is better for the money: GPT-6.1 Terra (Low) by OpenAI or MiMo-V2.6-Pro by Xiaomi? 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
MiMo-V2.6-Pro scores 10.1 points higher (46.3 vs 36.2) but costs 1.8× as much to run the benchmark ($207 vs $115; both mid-range class). Pick MiMo-V2.6-Pro when the extra intelligence is worth the premium, otherwise GPT-6.1 Terra (Low).
| Metric | GPT-6.1 Terra (Low) | MiMo-V2.6-Pro | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 36.2 | 46.3 | +27.9% MiMo-V2.6-Pro is 27.9% more intelligent |
| Total AA cost (lower is better) | $114.52 | $206.66 | +80.5% MiMo-V2.6-Pro is 80.5% more expensive |
| End-to-end time (lower is better) | 6.78s | 46.25s | +582.2% MiMo-V2.6-Pro is 582.2% slower |
| Price per 1M tokens (in / out) | $1.00 / $5.00 | $0.43 / $0.87 | |
| Input modalities | Text, Image | Text, Image, Speech, Video |
MiMo-V2.6-Pro vs GPT-6.1 Terra (Low): 27.9% more intelligence, 80.5% more cost to run the AA benchmark, and 582.2% slower end-to-end.
Today's Pareto frontier
Against the frontier
- GPT-6.1 Terra (Low) is off the frontier: at the same or lower cost, MiMo-V2.6-Flash scores 37.90 for $110.
- MiMo-V2.6-Pro is on today's frontier: nothing is both smarter and cheaper.
GPT-6.1 Terra (Low)MiMo-V2.6-ProToday'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-6-1-terra-low/mimo-v2-6-pro · Markdown: /api/v1/compare/gpt-6-1-terra-low/mimo-v2-6-pro?format=md · llms.txt · agent skill