Skip to main content
leaderboard
.cn
Toggle Sidebar
Search models or organizations…
⌘K
Explore
Frontier Models
Historical Trends
Local Models
Compare Models
Ranking Studio
Library
Models
Pricing
Organizations
Benchmarks
Data sources
Settings
Toggle Sidebar
leaderboard
.cn
Loading page content
Feedback
Loading page content
Back to models
MiniMax M3
Open
Share
Add to comparison
Tool use · Reasoning
Overview
Deployment
Pricing
Evaluations
Evaluation overview
Overall rank
#29
80.9 points · 180 models
Open-weight rank
#6
90 points · 109 models
Data coverage
47 items
7 sources · updated through 2026-07-16
Domain performance
Coding
#16 / 160
86
Research
#40 / 174
87.6
Agents
#23 / 125
80.7
Vision
#25 / 65
82.8
Long context
#27 / 82
80
Evaluation highlights
All evaluations
OmniDocBench 1.5
Multimodal · MiniMax M3 Technical Report
91.6%
1
/ 28
Claw Eval (pass^3)
Coding · MiniMax M3 Technical Report
74.5%
1
/ 21
GPQA-Diamond
Reasoning · GLM-5.2 Technical Report
93%
10
/ 126
SpreadSheetBench-v1
Agents · MiniMax M3 Technical Report
89.35%
1
/ 12
Arena Document Rating
Long context · Arena.ai Document
1,435.36Elo
17
/ 28
Arena Text Rating
Reasoning · Arena.ai Text
1,446.54Elo
48
/ 354
Basic information
Context (input / output)
1M / 16K
Parameters
428B / 23B active
Release date
2026-06
License
minimax-community
Input modalities
Text · Image · Video
Output modalities
Text
Active parameters
23B
Availability
MiniMax Open Platform
Full pricing
Input
≈ $0.3 /1M
Output
≈ $1.2 /1M
vLLM · BF16
Deployment options
BF16 · 8 × 141 GB VRAM
Related links
Official site
HuggingFace