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
Hunyuan 3
Open
Share
Add to comparison
Tool use · Reasoning
Overview
Deployment
Pricing
Evaluations
Evaluation overview
Overall rank
#45
81.8 points · 202 models
Open-weight rank
#13
85.3 points · 120 models
Data coverage
48 items
4 sources · updated through 2026-09-02
Domain performance
Coding
#35 / 182
80.9
Research
#44 / 196
89.2
Agents
#41 / 148
77.6
Long context
#14 / 95
86.9
Evaluation highlights
All evaluations
Arena Text Rating
Reasoning · Arena.ai Text
1,456.85Elo
46
/ 375
ProdBench (internal, Pass^3)
Agents · Hy3 Hugging Face README
23%
2
/ 10
CL-bench
Coding · Hy3 Hugging Face README
23.8%
3
/ 14
CL-bench life
Long context · Hy3 Hugging Face README
17%
3
/ 11
AA-LCR
Reasoning · Hy3 Hugging Face README
73.4%
7
/ 33
HorizonMath (pass@12)
Reasoning · Hy3 Hugging Face README
7.1%
2
/ 9
Basic information
Context (input / output)
262K / -
Parameters
295B / 21B active
Release date
2026-07
License
Apache 2.0
Input modalities
Text
Output modalities
Text
Architecture
MoE
Availability
Tencent Cloud
Full pricing
Input
≈ $0.1429 /1M
Output
≈ $0.5714 /1M
vLLM · FP8
Deployment options
FP8 · 8 × 141 GB VRAM
Related links
Official site
HuggingFace
ModelScope
Version relationships
Hy3 family
Hunyuan 3 Preview
2026-04 · Predecessor · Deprecated
Hunyuan 3
Current
2026-07 · Current model