Skip to content
#56BNov 20, 2025Evidence B

HunyuanVideo 1.5

Tencent · 8.3B dense

Open video generation at 8.3B

Tencent’s 8.3B video-generation model open-sourced in November 2025: generation 95, video 85, ecosystem 86 and a composite of 63.7. It is strong on short-video generation and camera motion; understanding is weak (perception 70, documents 55, agents 35), so it is not a multimodal analysis model.

TextImageVideoNative

Last updated Oct 21, 2026Editorial scoring

Bottom line

For short-video assets, ad storyboards and shot extension, HunyuanVideo 1.5 is a mature 8.3B open-weight option: generation 95, video 85, runnable on consumer GPUs. Do not judge it by its understanding scores — it is a generator, not an analyser.

Eight-dimension breakdown

editorial mapping · 0–100
Perception70Document55Chart QA40Video85Agent35Generation95Chinese80Ecosystem868D
  • HunyuanVideo 1.563.7
Visual perception & grounding20%
70
Document parsing & Chinese OCR18%
55
Chart & document reasoning14%
40
Video & long-horizon reasoning14%
85
GUI agents & tool use14%
35
Generation & editing6%
95
Chinese context & culture6%
80
Ecosystem, cost & availability8%
86

Weights: perception 20 / documents 18 / charts 14 / video 14 / agents 14 / generation 6 / Chinese 6 / ecosystem 8. Definitions and sources on the methodology page.

Public benchmarks

as reported, not converted
Benchmark / metricValueNote
参数规模8.3BOfficial spec
许可证社区许可Commercial use, not OSI
上下文16KFor generation tasks

Public scores come from different versions and prompts and are not interchangeable with our composite; they are one evidence input.

Scenario mapping

five stress tests, one scale
ScenarioScoreObservation
Short-video generation95 · Natural camera motion
Image generation90 · Good first-frame quality
30-min video QA85 · Generation only, not QA
Chinese receipt OCR55 · Not an OCR model
Chinese cultural context80 · Good response to Chinese-style prompts

Strengths and limitations

Strengths

  • Generation 95 and video 85 make it a mature open-weight video generator.
  • 8.3B and consumer-GPU support keep experimentation cheap.
  • Ecosystem 86: good ComfyUI and community workflow support.

Limitations

  • Perception 70 and documents 55: not for multimodal analysis.
  • Agents 35: no business automation.
  • The Tencent Hunyuan community licence is not OSI open source; check before commercial use.

Price and real cost

List price

—N/A

Open weights; runs on consumer GPUs. For 1,000 images at 1,024px, ~1,100 image tokens each and 300 output tokens, the monthly cost is about ¥0.0 (assuming input at 25% of output price).

Use your volume

About HunyuanVideo 1.5

Is HunyuanVideo 1.5 open source?

Licence: Open weights (Tencent Hunyuan community licence). Weights are available, but check the exact terms and filing requirements before commercial use.

How much does HunyuanVideo 1.5 cost?

Open weights; runs on consumer GPUs. It ranks #56 with a composite of 63.7. Real bills depend on resolution, tiling, caching and volume discounts.

What is HunyuanVideo 1.5 best for?

Short-video asset generation; Ad storyboards and shot extension; Local video-creation workflows。

Why does HunyuanVideo 1.5 score 63.7?

The composite weights eight dimensions: perception 20%, documents 18%, charts 14%, video 14%, agents 14%, generation 6%, Chinese 6%, ecosystem 8%. Its strongest dimension is Generation & editing; its weakest is GUI agents & tool use.

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.