GPT-6 Sol (Non-reasoning) vs MiniMax-M3
Which is better for the money: GPT-6 Sol (Non-reasoning) 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
MiniMax-M3 scores 0.7 points higher (29.2 vs 28.5) but costs 1.2× as much to run the benchmark ($538 vs $449; premium vs mid-range cost classes). Pick MiniMax-M3 when the extra intelligence is worth the premium, otherwise GPT-6 Sol (Non-reasoning).
| Metric | GPT-6 Sol (Non-reasoning) | MiniMax-M3 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 28.5 | 29.2 | +2.5% MiniMax-M3 is 2.5% more intelligent |
| Total AA cost (lower is better) | $449.37 | $537.98 | +19.7% MiniMax-M3 is 19.7% more expensive |
| End-to-end time (lower is better) | 5.91s | 25.25s | +327.2% MiniMax-M3 is 327.2% 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 (Non-reasoning): 2.5% more intelligence, 19.7% more cost to run the AA benchmark, and 327.2% slower end-to-end.
Today's Pareto frontier
Against the frontier
- GPT-6 Sol (Non-reasoning) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Medium) scores 47.80 for $361.
- 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 (Non-reasoning)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-non-reasoning/minimax-m3 · Markdown: /api/v1/compare/gpt-6-sol-non-reasoning/minimax-m3?format=md · llms.txt · agent skill