gpt-oss-20b (High) vs MiniMax-M3
Which is better for the money: gpt-oss-20b (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
MiniMax-M3 scores 20.2 points higher (29.2 vs 9.0) but costs 19× as much to run the benchmark ($538 vs $28.8; premium vs budget cost classes). They are not alternatives at one budget: pick MiniMax-M3 when you need intelligence above 9.0, and gpt-oss-20b (High) when 9.0 is enough.
| Metric | gpt-oss-20b (High) | MiniMax-M3 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 9.0 | 29.2 | +224.4% MiniMax-M3 is 3.2× more intelligent |
| Total AA cost (lower is better) | $28.81 | $537.98 | +1767.3% MiniMax-M3 is 19× more expensive |
| End-to-end time (lower is better) | 16.48s | 25.47s | +54.6% MiniMax-M3 is 54.6% slower |
| Price per 1M tokens (in / out) | $0.05 / $0.22 | $0.30 / $1.20 | |
| Input modalities | Text | Text, Image, Video |
MiniMax-M3 vs gpt-oss-20b (High): 224.4% more intelligence, 1767.3% more cost to run the AA benchmark, and 54.6% slower end-to-end.
Today's Pareto frontier
Against the frontier
- gpt-oss-20b (High) is off the frontier: at the same or lower cost, GPT-6 Luna (Low) scores 21.50 for $10.6.
- MiniMax-M3 is off the frontier: at the same or lower cost, GPT-6.1 Sol (High) scores 50.20 for $521.
gpt-oss-20b (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-oss-20b/minimax-m3 · Markdown: /api/v1/compare/gpt-oss-20b/minimax-m3?format=md · llms.txt · agent skill