Claude Opus 5 (Medium) vs MiniMax-M3
Which is better for the money: Claude Opus 5 (Medium) by Anthropic 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
Claude Opus 5 (Medium) scores 15.6 points higher (44.8 vs 29.2) but costs 5.1× as much to run the benchmark ($2732 vs $538; flagship vs premium cost classes). They are not alternatives at one budget: pick Claude Opus 5 (Medium) when you need intelligence above 29.2, and MiniMax-M3 when 29.2 is enough.
| Metric | Claude Opus 5 (Medium) | MiniMax-M3 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 44.8 | 29.2 | −34.8% MiniMax-M3 is 34.8% less intelligent |
| Total AA cost (lower is better) | $2,731.91 | $537.98 | −80.3% MiniMax-M3 is 80.3% cheaper |
| End-to-end time (lower is better) | 12.70s | 25.47s | +100.6% MiniMax-M3 is 100.6% slower |
| Price per 1M tokens (in / out) | $5.00 / $25.0 | $0.30 / $1.20 | |
| Input modalities | Text, Image | Text, Image, Video |
MiniMax-M3 vs Claude Opus 5 (Medium): 34.8% less intelligence, 80.3% less cost to run the AA benchmark, and 100.6% slower end-to-end.
Today's Pareto frontier
Against the frontier
- Claude Opus 5 (Medium) is off the frontier: at the same or lower cost, Claude Opus 5.5 (High, Default Fallback) scores 53.60 for $2172.
- MiniMax-M3 is off the frontier: at the same or lower cost, GPT-6.1 Sol (High) scores 50.20 for $521.
Claude Opus 5 (Medium)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/claude-opus-5-medium/minimax-m3 · Markdown: /api/v1/compare/claude-opus-5-medium/minimax-m3?format=md · llms.txt · agent skill