Compare Models

Select models (max 5)

MiniMax-M3Muse Spark Open


Vals IndexGDP-weighted benchmark	36.53%±1.17	46.61%±1.20
Legal Research BenchAgentic US legal research	29.81%±3.18	38.46%±3.38
Finance Agent (v2)Core financial analyst tasks	48.27%±0.44	61.34%±2.09
Tax Agent BenchAgentic US corporate tax research	20.59%±2.87	26.32%±2.65
MedCodeMedical billing code support	46.29%±2.10	N/A
Code MigrationRewriting programs in new languages	19.93%±3.94	21.17%±3.47
Terminal-Bench 4.0Frontier-difficulty terminal tasks	1.01%±1.01	6.57%±0.51
Vibe Code Bench v1.1Building web apps from scratch	47.57%±5.44	76.19%±3.32

Benchmarks

Vals Index *

MiniMax-M3

0.00%± 1.17

(49/49)

Muse Spark Open

0.00%± 1.20

(49/49)

Legal Research Bench *

MiniMax-M3

0.00%± 3.18

(79/79)

Muse Spark Open

0.00%± 3.38

(79/79)

Finance Agent (v2) *

MiniMax-M3

0.00%± 0.44

(79/79)

Muse Spark Open

0.00%± 2.09

(79/79)

Tax Agent Bench *

MiniMax-M3

0.00%± 2.87

(70/70)

Muse Spark Open

0.00%± 2.65

(70/70)

MedCode *

MiniMax-M3

0.00%± 2.10

(107/107)

Muse Spark Open

N/A

Code Migration *

MiniMax-M3

0.00%± 3.94

(78/78)

Muse Spark Open

0.00%± 3.47

(78/78)

Terminal-Bench 4.0

MiniMax-M3

0.00%± 1.01

(49/49)

Muse Spark Open

0.00%± 0.51

(49/49)

Vibe Code Bench v1.1 *

MiniMax-M3

0.00%± 5.44

(113/113)

Muse Spark Open

0.00%± 3.32

(113/113)

Overall performance

Performance on the Vals Index, a GDP-weighted aggregation of tasks across finance, coding, and law

•2026-10-16

MiniMax-M3 Muse Spark Open

Comparison by Industry

Model performance on different sections of the economy.

Legal

39.80%

vs.

27.56%

Finance

51.54%

vs.

47.11%

Healthcare

66.77%

vs.

N/A

Math

18.00%

vs.

N/A

Academic

86.02%

vs.

N/A

Education

50.57%

vs.

N/A

Coding

39.96%

vs.

34.64%

Cyber

65.00%

vs.

N/A

Social Mobility

64.14%

vs.

N/A

Cost Analysis

Per task and per token model pricing.

Vals Index · USD

$3.082

$4.077

Cost / TestVals Index

$3.082

vs.

$4.077

Input Cost/ 1M Tokens

$0.60

vs.

$1.25

Input Cache Read/ 1M Tokens

$0.12

vs.

$0.15

Output Cost/ 1M Tokens

$2.40

vs.

$4.25

Model Metadata

Basic information about each model.


Model provider	MiniMax	Together
Latency	2334.67s	4059.60s
Cost (In/Out)	$0.6 / $2.4	$1.25 / $4.25
Context Window	1M	1M
Max Output Token	512k	131k
Input Modality