MiniMax-M3 vs Muse Spark Open: price, speed and benchmarks

Muse Spark Open leads the intelligence index 24.9 to 18.9. MiniMax-M3 costs 74% less on blended price. Price per token, response speed and when to pick each.

Metric	MiniMax-M3	Muse Spark Open (Xhigh)
Intelligence Index	18.9	24.9
Input price (per 1M tokens)	$0.30	$1.25
Output price (per 1M tokens)	$1.20	$4.25
Output speed (tokens/s)	121	207
Time to first token	0.82s	0.94s
Release date	2026-06-01	2026-10-15

Metric

MiniMax-M3

Muse Spark Open (Xhigh)

Intelligence Index

18.9

24.9

Input price (per 1M tokens)

$0.30

$1.25

Output price (per 1M tokens)

$1.20

$4.25

Output speed (tokens/s)

121

207

Time to first token

0.82s

0.94s

Release date

2026-06-01

2026-10-15

This comparison puts MiniMax's MiniMax-M3 next to Meta's Muse Spark Open (Xhigh). Cost is where they split the most, with MiniMax-M3 working out at about 26% of Muse Spark Open's blended rate. All numbers are the catalogue's recorded values; nobody ran either model by hand for this page.

Running costs

MiniMax-M3 lists $0.30 per million input tokens and $1.20 per million output tokens; Muse Spark Open lists $1.25 and $4.25. Muse Spark Open costs 3.5 times as much per output token.

Take 1 million input tokens and 200,000 output tokens: that comes to $0.54 on MiniMax-M3 and $2.10 on Muse Spark Open. For a chat app with 50,000 sessions of 800 input and 300 output tokens, MiniMax-M3 would come in 74% lower: $30.00 for MiniMax-M3 against $114 for Muse Spark Open. Blended at three input tokens per output token, the effective rates are $0.525 for MiniMax-M3 and $2.00 for Muse Spark Open.

Muse Spark Open is the faster writer

MiniMax-M3 generates about 121 tokens per second and Muse Spark Open about 207 tokens per second. That makes Muse Spark Open roughly 1.7 times as fast at writing. Time to first token is 0.82 seconds for MiniMax-M3 and 0.94 seconds for Muse Spark Open.

Put together, a 2,000-token answer would take about 17 seconds from MiniMax-M3 and 11 seconds from Muse Spark Open, counting the first-token wait. Counting that wait, Muse Spark Open only pulls ahead on outputs beyond about 50 tokens.

Generation gap

The release dates are June 1, 2026 for MiniMax-M3 and October 15, 2026 for Muse Spark Open, about 4 months apart.

The headline benchmark

On the intelligence index, MiniMax-M3 scores 18.9 against 24.9 for Muse Spark Open. It is a meaningful gap rather than a rounding difference. Put another way, MiniMax-M3 would need 32% more on this index to draw level.

Among 109 active scored models, MiniMax-M3 sits 79th and Muse Spark Open 68th.

There are no coding or math index scores for either model in the catalogue, which keeps this comparison at the aggregate level.

Score per dollar

Per point of intelligence index, MiniMax-M3 costs $0.028 of blended price per million tokens and Muse Spark Open $0.080. So Muse Spark Open buys its higher score at a premium, while MiniMax-M3 is the value pick, paying 65% less per point.

FAQ

Is MiniMax-M3 better than Muse Spark Open?

It depends on what you need: Muse Spark Open scores higher on the intelligence index, 24.9 to 18.9; MiniMax-M3 is 74% cheaper on blended price; and Muse Spark Open streams output 1.7 times as fast.

Is Muse Spark Open cheaper than MiniMax-M3?

MiniMax-M3 is cheaper on a blended basis. MiniMax-M3 lists $0.30 per million input tokens and $1.20 per million output tokens; Muse Spark Open lists $1.25 and $4.25. For 1 million input and 200,000 output tokens that is $0.54 against $2.10.

Was this comparison tested by hand?

The figures are the recorded benchmark, price and speed data in Franklin AI's model catalogue. This page is written from that data automatically; neither model was tested by hand for it.

Which is faster, MiniMax-M3 or Muse Spark Open?

Muse Spark Open generates output faster, at 207 tokens per second against 121 tokens per second. Time to first token is similar: 0.82 seconds and 0.94 seconds. Counting the first-token wait, MiniMax-M3 finishes short replies first and Muse Spark Open pulls ahead beyond about 50 tokens.

Who makes MiniMax-M3 and Muse Spark Open?

MiniMax-M3 is made by MiniMax and Muse Spark Open by Meta. MiniMax-M3 was released on June 1, 2026 and Muse Spark Open on October 15, 2026.

Final whistle

Short answer: Muse Spark Open has more going for it here, but MiniMax-M3 is not without an argument. Pick Muse Spark Open if you need the higher overall score (24.9 against 18.9) and your outputs often run past about 50 tokens. Pick MiniMax-M3 if cost matters ($1.20 against $4.25 per million output tokens).

Where the numbers come from

The scores, speed and prices in this comparison come from independent third-party model evaluations that Franklin AI syncs each day, and the article was written from a snapshot of them. For the latest results, open the MiniMax-M3 and Muse Spark Open (Xhigh) pages. The AI Benchmark methodology explains how that data is collected and shown.