General Agents Benchmark

DeepresearchBII

DeepresearchBII - deep-research agentic benchmark used in Xing4.0-29B-A4B and competitor model cards. Evaluation setup as printed: OpenCode harness with an Exa MCP server enabled, temperature=0.8, top_p=0.95, repetition_penalty=1.05, max_tokens=32768, 256K context window.

Category

General Agents

Score type

percent

Scale

100%

higher is better

Models tested

1

What is DeepresearchBII?

DeepresearchBII is a benchmark for how well a model acts as a general-purpose agent. The official description says: "DeepresearchBII - deep-research agentic benchmark used in Xing4.0-29B-A4B and competitor model cards". Below we describe in simple words what benchmarks of this type generally examine.

What does it test?

DeepresearchBII 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: DeepresearchBII - deep-research agentic benchmark used in Xing4.0-29B-A4B and competitor model cards. Evaluation setup as printed: OpenCode harness with an Exa MCP server enabled, temperature=0.8, top_p=0.95, repetition_penalty=1.05, max_tokens=32768, 256K context window.

Frequently asked questions

What is the DeepresearchBII benchmark?

DeepresearchBII is a benchmark for how well a model acts as a general-purpose agent. The official description says: 'DeepresearchBII - deep-research agentic benchmark used in Xing4.0-29B-A4B and competitor model cards'. Below we describe in simple words what benchmarks of this type generally examine.

What does DeepresearchBII test?

DeepresearchBII 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 DeepresearchBII 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 DeepresearchBII 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/deepresearch-bii/scores) or pull it directly from the Open LLM Radar API with any HTTP client.

Model scores 1 model tested

Reset
# Model Score Date Source Verified
1 Xing4.0-29B-A4B
China Telecom AI
60.8%
16.09.2026 Report Verified

What now?

You've seen how models score on DeepresearchBII — here's what to do next.