Claude Sonnet 5 (High) vs MiniMax-M3
Which is better for the money: Claude Sonnet 5 (High) 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 Sonnet 5 (High) scores 2.5 points higher (31.7 vs 29.2) but costs 3.9× as much to run the benchmark ($2086 vs $538; flagship vs premium cost classes). They are not alternatives at one budget: pick Claude Sonnet 5 (High) when you need intelligence above 29.2, and MiniMax-M3 when 29.2 is enough.
| Metric | Claude Sonnet 5 (High) | MiniMax-M3 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 31.7 | 29.2 | −7.9% MiniMax-M3 is 7.9% less intelligent |
| Total AA cost (lower is better) | $2,086.04 | $537.98 | −74.2% MiniMax-M3 is 74.2% cheaper |
| End-to-end time (lower is better) | 15.23s | 25.47s | +67.2% MiniMax-M3 is 67.2% 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 Claude Sonnet 5 (High): 7.9% less intelligence, 74.2% less cost to run the AA benchmark, and 67.2% slower end-to-end.
Today's Pareto frontier
Against the frontier
- Claude Sonnet 5 (High) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 51.80 for $1082.
- MiniMax-M3 is off the frontier: at the same or lower cost, GPT-6.1 Sol (High) scores 50.20 for $521.
Claude Sonnet 5 (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/claude-sonnet-5-high/minimax-m3 · Markdown: /api/v1/compare/claude-sonnet-5-high/minimax-m3?format=md · llms.txt · agent skill