Benchmark Almanac

Hunyuan-4B-Instruct

Hunyuan-4B-Instruct.

Tencent Released July 30th, 2025 Family Hunyuan The lab's model card Compare with others
3
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Tencent Jul 2025

Hunyuan-4B-Instruct

Open weights Small

No Epoch Capabilities Index score yet
  • Angry Tweets 36.1% #128 /149
  • AgentIF (2026-10 setting) 54.4% #22 /24
  • Dutch Book Reviews Dataset 74.9% #86 /105

Where it ranks

Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.

Knowledge and language

BenchmarkScoreRankSource
Dutch Book Reviews Dataset 74.9% #86 of 105 Official leaderboard
Angry Tweets 36.1% #128 of 149 Official leaderboard
AgentIF (2026-10 setting) 54.4% #22 of 24 Official leaderboard

Who measured it?

Independent runs cover all 3 of its benchmarks.

  • An independent run only 3
Official leaderboards scored it on 3.

Sources: Official leaderboards, Epoch AI (CC BY 4.0) and labs’ model cards