MiMo-V2.6-Pro vs Muse Spark Open: speed, latency and cost

MiMo-V2.6-Pro leads the intelligence index 29.9 to 24.9. MiMo-V2.6-Pro costs 73% less on blended price. Benchmarks, sample bills, speed and a verdict.

Metric	MiMo-V2.6-Pro	Muse Spark Open (Xhigh)
Intelligence Index	29.9	24.9
Input price (per 1M tokens)	$0.435	$1.25
Output price (per 1M tokens)	$0.87	$4.25
Output speed (tokens/s)	41	207
Time to first token	3.0s	0.94s
Release date	2026-09-21	2026-10-15

Metric

MiMo-V2.6-Pro

Muse Spark Open (Xhigh)

Intelligence Index

29.9

24.9

Input price (per 1M tokens)

$0.435

$1.25

Output price (per 1M tokens)

$0.87

$4.25

Output speed (tokens/s)

207

Time to first token

3.0s

0.94s

Release date

2026-09-21

2026-10-15

MiMo-V2.6-Pro (Xiaomi) and Muse Spark Open (Xhigh) (Meta) meet here on their recorded benchmark, price and speed data. This page is written automatically from catalogue numbers only: benchmark scores, list prices and measured speed. Throughput is the standout difference: 207 tokens per second for Muse Spark Open against 41 tokens per second for MiMo-V2.6-Pro.

Waiting time

MiMo-V2.6-Pro generates about 41 tokens per second and Muse Spark Open about 207 tokens per second. On long outputs, that is a real advantage for Muse Spark Open. Before any text appears, MiMo-V2.6-Pro takes 3.0 seconds and Muse Spark Open 0.94 seconds. MiMo-V2.6-Pro waits 3.2 times as long before its first token.

For an 800-token response, first token plus generation comes to roughly 23 seconds on MiMo-V2.6-Pro and 4.8 seconds on Muse Spark Open.

What they cost

The list prices are $0.435 in and $0.87 out for MiMo-V2.6-Pro, and $1.25 in and $4.25 out for Muse Spark Open, per million tokens. For output tokens, Muse Spark Open is 4.9 times the price of MiMo-V2.6-Pro.

Take 1 million input tokens and 200,000 output tokens: that comes to $0.61 on MiMo-V2.6-Pro and $2.10 on Muse Spark Open. For writing 2,000 drafts of 2,000 output tokens from 300-token prompts, MiMo-V2.6-Pro would come in 79% lower: $3.74 for MiMo-V2.6-Pro against $17.75 for Muse Spark Open.

How the intelligence index compares

On the intelligence index, MiMo-V2.6-Pro scores 29.9 against 24.9 for Muse Spark Open. A lead of this size is hard to dismiss as noise. Put another way, Muse Spark Open would need 20% more on this index to draw level.

Among 109 active scored models, MiMo-V2.6-Pro sits 55th and Muse Spark Open 68th.

Specialist coding and math indexes are missing for both, so treat the overall score as the only capability signal here.

Cost per point of intelligence

Dividing the blended price by the intelligence index gives a rough cost per point: $0.018 for MiMo-V2.6-Pro and $0.080 for Muse Spark Open, per million tokens. MiMo-V2.6-Pro scores higher and costs less per point, so on price per point there is nothing to trade off.

Generation gap

Muse Spark Open arrived on October 15, 2026, 24 days after MiMo-V2.6-Pro (September 21, 2026). That is close enough to count them as the same generation.

FAQ

Is Muse Spark Open better than MiMo-V2.6-Pro?

Neither wins everywhere: MiMo-V2.6-Pro scores higher on the intelligence index, 29.9 to 24.9; MiMo-V2.6-Pro is 73% cheaper on blended price; and Muse Spark Open streams output 5 times as fast.

Which is newer, MiMo-V2.6-Pro or Muse Spark Open?

Muse Spark Open is newer. It was released on October 15, 2026, 24 days after MiMo-V2.6-Pro (September 21, 2026).

Which model has lower latency?

Muse Spark Open generates output faster, at 207 tokens per second against 41 tokens per second. Muse Spark Open reaches its first token sooner (0.94 seconds against 3.0 seconds).

Which is cheaper, MiMo-V2.6-Pro or Muse Spark Open?

MiMo-V2.6-Pro is cheaper on a blended basis. MiMo-V2.6-Pro lists $0.435 per million input tokens and $0.87 per million output tokens; Muse Spark Open lists $1.25 and $4.25. For 1 million input and 200,000 output tokens that is $0.61 against $2.10.

Who makes MiMo-V2.6-Pro and Muse Spark Open?

MiMo-V2.6-Pro is made by Xiaomi and Muse Spark Open by Meta. MiMo-V2.6-Pro was released on September 21, 2026 and Muse Spark Open on October 15, 2026.

Final whistle

Bottom line: MiMo-V2.6-Pro has more going for it here, but Muse Spark Open is not without an argument. Pick MiMo-V2.6-Pro if cost matters ($0.87 against $4.25 per million output tokens) and you need the higher overall score (29.9 against 24.9). Pick Muse Spark Open if long outputs need to finish quickly and users are waiting on the first word.

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 MiMo-V2.6-Pro and Muse Spark Open (Xhigh) pages. The AI Benchmark methodology explains how that data is collected and shown.