readable AI benchmarks

MiniMax

MiniMax-M3

reasoning · open weights · Jun 1, 2026

Quality Score46.4
Value Score40.2
Reliability50.7
Cache Discount80%

Model specification

Reasoning
reasoning
Input modalities
text, image, video
Output modalities
text
Context window
1M tokens
Weights
open weights

Token prices USD per 1M tokens

Input
$0.300
Output
$1.20
Cached Input
$0.060
Cached Output
$0.375
Cost per task
$0.139

Capability

Intelligence
45.4
Coding
58.6
Agentic
36.1
Omniscience
1.4
Correct
16.7%
Blended price
$0.222

Answer outcomes

Correct 16.7%Incorrect 15.3%Abstained 68.0%

Artificial Analysis benchmarks

GDPval-AA v2
44%
τ³-Banking
15%
Terminal-Bench v2.1
65%
SciCode
45%
Humanity’s Last Exam
39%
GPQA Diamond
93%
CritPt
4%
AA-Omniscience
51%
AA-LCR
80%

Similar models