Artificials
Compare models
All makers

AI model maker

Tencent

3 models on Artificials, 2 with published test results and 1 with open weights you can download.

RSS feed
Best on the capability indexNot yetNone of its models is on the index yet
Best rankTop 8%Hy3 on Arena math
Newest releaseHunyuan-T1Mar 8, 2026
Models32 tested, 1 with open weights

Where Tencent stands

Its best model’s rank among all models tested on each skill area’s main test, the same tests model pages use. A longer bar means a better rank.

  • OverallHy3 on Arena text
    Top 15%
  • CodingHy3 on Arena coding
    Top 18%
  • MathHy3 on Arena math
    Top 8%
  • LanguageHy3 on Arena creative writing
    Top 18%
  • ReasoningHy3 on Arena hard prompts
    Top 16%
  • Image generationHunyuanImage 3.0 on T2I-CoReBench
    Top 40%

Every test

Its best result on each published test, and that result’s rank among every model tested. Scores from different tests are never combined.

TestBest modelScoreRank
Arena mathHy31480#29 of 372
Arena WebDevHy4 preview1633#15 of 123
Arena textHy31456#56 of 389
Arena hard promptsHy31476#61 of 389
Arena instruction followingHy31446#61 of 389
Arena codingHy31500#67 of 384
Arena creative writingHy31422#68 of 387
T2I-CoReBenchHunyuanImage 3.058.7%#16 of 40

Every model

Newest first. The price is per 1M tokens, blended three input tokens to one output token: Tencent’s own listing, or else the middle price across hosts.

ModelReleasedContextPriceCapability index
Hunyuan-T1Mar 8, 2026131.1K tokensNo paid listingNot on the index
Hunyuan-TurboSMar 8, 2026131.1K tokensNo paid listingNot on the index
Hunyuan A13B InstructJun 30, 2025131.1K tokens$0.248Not on the index

Models, prices, context windows and release dates from models.dev (MIT). Test results from T2I-CoReBench (CC BY-SA 4.0) and Arena (CC BY 4.0). A model counts here when Tencent sells it, several hosts list it or a test covers it. Each figure is the source’s own; nothing is combined into a new score.