General Agents Benchmark

Hy-CompanyBench V2 (Internal)

Tencent internal (Hy team) agentic search / company-work benchmark, reported in the Hy4 preview model card appendix.

Category

General Agents

Score type

percent

Scale

100%

higher is better

Models tested

5

What is Hy-CompanyBench V2 (Internal)?

Hy-CompanyBench V2 (Internal) is a benchmark for how well a model acts as a general-purpose agent. The official description says: "Tencent internal (Hy team) agentic search / company-work benchmark, reported in the Hy4 preview model card appendix". Below we describe in simple words what benchmarks of this type generally examine.

What does it test?

Hy-CompanyBench V2 (Internal) measures how well a model acts as a general-purpose agent. In detail, it checks:

  • solving long, multi-step tasks with many intermediate decisions
  • using tools correctly (browsers, terminals, APIs, calendars, other apps)
  • adapting when something unexpected happens mid-task
  • staying on goal over long task horizons instead of wandering off

How to read the score

The score is accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better.

Official methodology note: Tencent internal (Hy team) agentic search / company-work benchmark, reported in the Hy4 preview model card appendix.

Frequently asked questions

What is the Hy-CompanyBench V2 (Internal) benchmark?

Hy-CompanyBench V2 (Internal) is a benchmark for how well a model acts as a general-purpose agent. The official description says: 'Tencent internal (Hy team) agentic search / company-work benchmark, reported in the Hy4 preview model card appendix'. Below we describe in simple words what benchmarks of this type generally examine.

What does Hy-CompanyBench V2 (Internal) test?

Hy-CompanyBench V2 (Internal) mainly measures how well a model acts as a general-purpose agent. Concretely, it checks: solving long, multi-step tasks with many intermediate decisions; using tools correctly (browsers, terminals, APIs, calendars, other apps); adapting when something unexpected happens mid-task.

How is the Hy-CompanyBench V2 (Internal) score calculated?

The score is accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better. The declared maximum score of this benchmark is 100.0.

Where do I get Hy-CompanyBench V2 (Internal) data and scores?

The official benchmark page/reference is linked on this page. Every score on Open LLM Radar is also available as open data: download the scores JSON (http://open-llm-radar-api:8000/api/v1/benchmarks/hy-companybench-v2-internal/scores) or pull it directly from the Open LLM Radar API with any HTTP client.

Model scores 5 models tested

Reset
# Model Score Date Source Verified
1 GLM-5.3
Zhipu AI
64.5%
28.08.2026 Tencent Hy4 preview model card benchmark appendix (https://huggingface.co/tencent/Hy4-preview#benchmark-appendix) (Tencent rerun) Verified
2 Qwen3.8-2.4T-A95B
Qwen
63.3%
28.08.2026 Tencent Hy4 preview model card benchmark appendix (https://huggingface.co/tencent/Hy4-preview#benchmark-appendix) (Tencent rerun) Verified
3 Kimi K3
Moonshot AI
63.3%
28.08.2026 Tencent Hy4 preview model card benchmark appendix (https://huggingface.co/tencent/Hy4-preview#benchmark-appendix) (Tencent rerun) Verified
4 Hy4 preview
Tencent
62.4%
28.08.2026 Tencent Hy4 preview model card benchmark appendix (https://huggingface.co/tencent/Hy4-preview#benchmark-appendix) Verified
5 Hy3
Tencent
29.8%
28.08.2026 Tencent Hy4 preview model card benchmark appendix (https://huggingface.co/tencent/Hy4-preview#benchmark-appendix) Verified

What now?

You've seen how models score on Hy-CompanyBench V2 (Internal) — here's what to do next.