MiniMax-M3
By MiniMax · released 2026-06-01 (2 months) · snapshot 2026-08-07
- Intelligence index
- 45.40
- Cost to run the AA index
- $205
- Price per 1M tokens (in / out)
- $0.30 / $1.20
- End-to-end time
- 27.3s
Is MiniMax-M3 on the Pareto frontier, and what beats it?
Off the frontier
No. GPT-5.6 Luna (max) is at least as smart for the same money or less.
Next step up: Muse Spark 1.1 (xhigh), smarter but dearer.
| # | Model | Creator | Intelligence | Total cost | E2E total | Open | Released | Frontier |
|---|---|---|---|---|---|---|---|---|
| 1 | MiniMax-M3 | MiniMax | 45.40 | $205 | 27.3s | 2026-06-01 | ||
| 2 | GPT-5.6 Luna (max) | OpenAI | 52.30 | $172 | 106.4s | 2026-07-09 | Frontier | |
| 3 | Muse Spark 1.1 (xhigh) | Meta | 53.20 | $547 | 13.7s | 2026-07-09 | Frontier |
Open in the picker Daily check URL: 200 on the frontier, 409 once beaten
MiniMax-M3 today
Intelligence: Artificial Analysis Intelligence Index. Cost: total cost to run that benchmark, so reasoning tokens count. API id: minimax-m3.
Compare head to head
Suggested: what beats it, its effort levels, and frontier models near its price.
What the MiniMax-M3 release did to the frontier on 2026-06-01
1 of 1 effort levels reached the frontier at launch (MiniMax-M3). Impact 0.06, #39 of 41 releases this past year.
Should you use MiniMax-M3?
Should you use MiniMax-M3?
Only when it fits your setup: GPT-5.6 Luna (max) is at least as smart for the same money or less, so MiniMax-M3 is off the value frontier today.
What is better and cheaper than MiniMax-M3?
GPT-5.6 Luna (max) — at least as smart for the same money or less.
How much does MiniMax-M3 cost?
$0.30/$1.20 in/out per 1M tokens, and $205 to run the full Artificial Analysis Intelligence Index, the honest all-in number for reasoning models.
Is MiniMax-M3 on the Pareto frontier?
No: GPT-5.6 Luna (max) beats it on intelligence, cost, or both.
Frontier membership by axis pair
Other axis pairs where MiniMax-M3 is Pareto-optimal.
| Y axis | X axis | On the frontier |
|---|---|---|
| AA intelligence index | AA total cost to run (USD) | |
| AA intelligence index | End-to-end total seconds | |
| AA intelligence index | Output speed tokens/sec |
Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/models/minimax-m3 · Markdown: /api/v1/models/minimax-m3?format=md · llms.txt · agent skill