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
Max Score
100.0
Score Type
percent
Active
Yes
Model Scores
Scores for DeepresearchBII
| Model | Score | Date | Verified |
|---|---|---|---|
| Xing4.0-29B-A4B |
60.80%
|
16.09.2026 | Verified |