GPT-6 Sol (High) vs MiniMax-M3
Which is better for the money: GPT-6 Sol (High) by OpenAI or MiniMax-M3 by MiniMax? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-25.
Trade-off
Verdict
Depends on your budget
GPT-6 Sol (High) scores 13.2 points higher (42.4 vs 29.2) but costs 1.1× as much to run the benchmark ($605 vs $538; both premium class). Pick GPT-6 Sol (High) when the extra intelligence is worth the premium, otherwise MiniMax-M3.
| Metric | GPT-6 Sol (High) | MiniMax-M3 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 42.4 | 29.2 | −31.1% MiniMax-M3 is 31.1% less intelligent |
| Total AA cost (lower is better) | $604.52 | $537.98 | −11.0% MiniMax-M3 is 11.0% cheaper |
| End-to-end time (lower is better) | 14.77s | 25.47s | +72.4% MiniMax-M3 is 72.4% slower |
| Price per 1M tokens (in / out) | $2.00 / $10.0 | $0.30 / $1.20 | |
| Input modalities | Text, Image | Text, Image, Video |
MiniMax-M3 vs GPT-6 Sol (High): 31.1% less intelligence, 11.0% less cost to run the AA benchmark, and 72.4% slower end-to-end.
Today's Pareto frontier
Against the frontier
- GPT-6 Sol (High) is off the frontier: at the same or lower cost, GPT-6.1 Sol (High) scores 50.20 for $521.
- MiniMax-M3 is off the frontier: at the same or lower cost, GPT-6.1 Sol (High) scores 50.20 for $521.
GPT-6 Sol (High)MiniMax-M3Today'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-sol-high/minimax-m3 · Markdown: /api/v1/compare/gpt-6-sol-high/minimax-m3?format=md · llms.txt · agent skill