Claude Haiku 5.5 (Max) vs MiniMax-M3
Which is better for the money: Claude Haiku 5.5 (Max) 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.
Clear winner
Verdict
Pick Claude Haiku 5.5 (Max)
MiniMax-M3 vs Claude Haiku 5.5 (Max): 32.7% less intelligence, 62.9% more cost to run the AA benchmark, and 92.2% faster end-to-end.
| Metric | Claude Haiku 5.5 (Max) | MiniMax-M3 | Difference |
|---|---|---|---|
| Intelligence (higher is better) | 43.4 | 29.2 | −32.7% MiniMax-M3 is 32.7% less intelligent |
| Total AA cost (lower is better) | $330.25 | $537.98 | +62.9% MiniMax-M3 is 62.9% more expensive |
| End-to-end time (lower is better) | 318.47s | 24.85s | −92.2% MiniMax-M3 is 92.2% faster |
| Price per 1M tokens (in / out) | $0.10 / $0.50 | $0.30 / $1.20 | |
| Input modalities | Text, Image | Text, Image, Video |
Today's Pareto frontier
Against the frontier
- Claude Haiku 5.5 (Max) is off the frontier: at the same or lower cost, MiMo-V2.6-Pro scores 46.30 for $207.
- MiniMax-M3 is off the frontier: at the same or lower cost, GPT-6.1 Sol (High) scores 50.20 for $521.
Claude Haiku 5.5 (Max)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-haiku-5-5/minimax-m3 · Markdown: /api/v1/compare/claude-haiku-5-5/minimax-m3?format=md · llms.txt · agent skill