Tier
Major
Headquarters
Shenzhen, China
Founded
1998
Flagship
Hunyuan
Models tracked
3
Artificial Analysis
Top intelligence
41.2
Artificial Analysis Index
Cheapest model
$0.11
blended /1M
Fastest output
158
tokens / sec
Flagship Model
Tencent’s top-scoring model on the Artificial Analysis Intelligence Index.
Most intelligent model
Hy3
Released 2026-07-06
Intelligence
41.2
Coding
58.8
Math
—
In $/1M
$0.14
Out $/1M
$0.56
Speed t/s
68
Benchmark breakdown
Models & benchmarks
Every Tencent model on file — intelligence, coding, price, and speed.
| Model | Released | Intel | Coding | Math | In $/1M | Out $/1M | Speed t/s | Latency s |
|---|---|---|---|---|---|---|---|---|
| Hy3 | 2026-07-06 | 41.2 | 58.8 | — | $0.14 | $0.56 | 68 | 1.68 |
| Hy3-preview (Reasoning) | 2026-04-23 | 33.6 | — | — | $0.07 | $0.23 | 158 | 1.80 |
| Hy3-preview (Non-reasoning) | 2026-04-23 | 26.1 | — | — | $0.07 | $0.23 | 150 | 1.64 |
Trajectory
Tencent’s model releases over time, by intelligence.
House strengths
Where Tencent’s lineup over-indexes, averaged across its models.
Capability profile
Best value
Hy3-preview (Reasoning)
Most intelligence per dollar — 33.6 index at $0.11/1M blended.
314 index points per $1
Governance
Tencent’s license posture and openness across its lineup.
Open weight
1
of 1 models
Proprietary
0
of 1 models
Commercial-OK
1
license permits
Modalities
—
Via LLM Stats
Media models
Image, video, and speech models, ranked by arena Elo.
| Model | Type | Released | Elo | Rank |
|---|---|---|---|---|
| HunyuanImage 3.0 Instruct (Fal) | image editing | 2026-01 | 1224 | #9 |
| HunyuanVideo-1.5 (Fal) | image to video | 2025-11 | 1126 | #54 |
| HunyuanImage 3.0 (Fal) | text to image | 2025-09 | 1126 | #56 |
| HunyuanImage 3.0 Instruct (Fal) | text to image | 2026-01 | 1119 | #62 |
| SRPO | text to image | 2025-09 | 1080 | #83 |
| HunyuanImage 2.1 | text to image | 2025-09 | 1065 | #95 |
| HunyuanVideo-1.5 (Fal) | text to video | 2025-11 | 1019 | #57 |
| Hunyuan Video (Fal) | text to video | 2024-12 | 997 | #64 |
| Hunyuan Video (Fal) | image to video | 2024-12 | 912 | #70 |