Head-to-head
Wan2.2 vs HunyuanVideo 1.5
A 1.4-point composite gap — but the real story is the dimension mix. Same weights, unpacked: who leads where, and whether the premium is justified.
The short answer
The composites differ by 1.4 points, and their strengths do not overlap.
Stronger overall: Wan2.2. If you only run one workload, read the dimension table instead.
Overlaid radar
Same weights, same scale; overlap means parity
- Wan2.265.1
- HunyuanVideo 1.563.7
Dimension deltas
A on the left, B on the right; 100 max per row
Wan2.2 leads 5, HunyuanVideo 1.5 leads 1, tied 2.
Spec sheet
Hard specs in one table
| Item | Wan2.2 | HunyuanVideo 1.5 |
|---|---|---|
| Composite | 65.1 | 63.7 |
| Tier | B | B |
| Visual perception & grounding | 72WIN | 70 |
| Document parsing & Chinese OCR | 55 | 55 |
| Chart & document reasoning | 40 | 40 |
| Video & long-horizon reasoning | 86WIN | 85 |
| GUI agents & tool use | 40WIN | 35 |
| Generation & editing | 94 | 95WIN |
| Chinese context & culture | 82WIN | 80 |
| Ecosystem, cost & availability | 88WIN | 86 |
| Output price | ¥0 / M | ¥0 / M |
| Context | 16K | 16K |
| Parameters | 27B total / 14B active (MoE) | 8.3B dense |
| Licence | Open weights (Apache-2.0) | Open weights (Tencent Hunyuan community licence) |
| Native multimodal | Yes | Yes |
| Evidence grade | A | B |
How to choose
Choose Wan2.2 if…
- Video generation and stylisation
- ComfyUI workflows
- A base for video-model fine-tuning
- You cannot accept its limitation: Perception 72 and documents 55: not for multimodal analysis.
How to choose
Choose HunyuanVideo 1.5 if…
- Short-video asset generation
- Ad storyboards and shot extension
- Local video-creation workflows
- You cannot accept its limitation: Perception 70 and documents 55: not for multimodal analysis.
Scenario check
Five scenarios, who holds up
| Scenario | Wan2.2 | HunyuanVideo 1.5 | Better |
|---|---|---|---|
| Short-video generation | 94 | 95 | HunyuanVideo 1.5 |
| Image generation | 90 | 90 | Tie |
| 30-min video QA | 86 | 85 | Wan2.2 |
| Chinese receipt OCR | 55 | 55 | Tie |
| Chinese cultural context | 82 | 80 | Wan2.2 |
Comparison FAQ
Wan2.2 vs HunyuanVideo 1.5: which is stronger?
Composite: Wan2.2 65.1, HunyuanVideo 1.5 63.7. Wan2.2 leads on Visual perception & grounding, Video & long-horizon reasoning, GUI agents & tool use, Chinese context & culture, Ecosystem, cost & availability; HunyuanVideo 1.5 leads on Generation & editing. The stronger overall is Wan2.2.
How much more expensive is Wan2.2 than HunyuanVideo 1.5?
Wan2.2 is ¥0/1M output tokens; HunyuanVideo 1.5 is ¥0/1M. On output price, Wan2.2 is pricier; real cost also depends on image tokens and input share.
Can HunyuanVideo 1.5 replace Wan2.2?
It depends on your primary workload. If it sits in HunyuanVideo 1.5’s strengths (Short-video asset generation, Ad storyboards and shot extension, Local video-creation workflows), yes. If you need Video generation and stylisation, switching will cost quality.
Personal ranking · Not an official score
Every ranking, score and comparison on this page is an independent personal ranking, not an official score, and represents no vendor, institution or regulator. Scores are a subjective mapping of public evidence under our own weights — change the weights and the order changes. Disagree, or spotted a factual error? Contact the site owner: jizhi2024@foxmail.com — we check each report and log corrections in the changelog.