Hy3 is Tencent's 295B-parameter Mixture-of-Experts model with 21B active parameters, native 256K context, and configurable reasoning modes. It is built for coding, long-context comprehension, multi-turn dialogue, and agentic task execution with a focus on high-throughput production workloads.
Added Jul 6, 2026
Model weightsContext Window
262.1K
Max Output
262.1K
Input Price (Auto)
$0.066/1M
Output Price (Auto)
$0.26/1M
Cache Read (Auto)
$0.029/1M
Capabilities
Benchmarks
Benchmarks
Performance metrics and benchmarks
Sourced from Design Arena.
Best Category
3D
Best Elo
1229
Best Rank Percentile
Top 35%
Ranking Distribution
4,047 battles
60%
45%
30%
15%
0%
7.0%
First
29.9%
Second
42.7%
Third
20.4%
Fourth
Category Performance
Models Arena
3D
1229
Elo
43.8%
Win
119.6s
Avg Time
#50
Rank
Website
1194
Elo
41.4%
Win
146.5s
Avg Time
#75
Rank
UI Component
1191
Elo
40.2%
Win
129.6s
Avg Time
#74
Rank
Game Development
1174
Elo
38.6%
Win
89.4s
Avg Time
#83
Rank
Data Visualization
1149
Elo
36.1%
Win
97.3s
Avg Time
#97
Rank
Updated Aug 24, 2026, 8:31 PM · Matched as Hy3
Design ArenaProviders
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Related text models
Compare Tencent Hy3 with similar models from the same provider or model family.
Hunyuan MT 7B
tencent/Hunyuan-MT-7BTencent's Hunyuan MT 7B translation model for fast multilingual text generation.
Hunyuan Turbo S
hunyuan-turbos-20250226Hunyuan Turbo S by Tencent is a thinking model that responds instantly.
Ornith 1.5 35B
ornith-ai/ornith-1.5-35b-a3bOrnith 1.5 35B A3B is an open-weight mixture-of-experts model for agentic coding, tool use, image understanding, and long-context work. This variant disables thinking for faster direct responses.
Ornith 1.5 35B Thinking
ornith-ai/ornith-1.5-35b-a3b:thinkingOrnith 1.5 35B A3B is an open-weight mixture-of-experts model for agentic coding, reasoning, tool use, image understanding, and long-context work. This variant enables thinking by default.
Qwen3.5 0.8B
qwen3.5-0.8bQwen3.5 0.8B is a lightweight open-weight multimodal model from Alibaba for fast reasoning, visual understanding, tool use, and JSON output.
Qwen3.5 2B
qwen3.5-2bQwen3.5 2B is a small open-weight multimodal model from Alibaba for efficient reasoning, coding, visual understanding, tool use, and JSON output.