Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Chinese Web Navigation Agentic Reasoning on BrowseComp ZH
Loading...
84.4
Avg@3
MiroThinker-H1
45.192
55.371
65.55
75.729
Mar 16, 2026
Avg@3
Updated 1mo ago
Evaluation Results
Method
Method
Links
Avg@3
MiroThinker-H1
Agent Style=ReAct, Max...
2026.03
84.4
Seed-2.0-Pro
Agent Style=ReAct, Max...
2026.03
82.4
MiroThinker-1.7
Agent Style=ReAct, Max...
2026.03
75.3
GLM-5.0
Agent Style=ReAct, Max...
2026.03
72.7
MiroThinker-1.7-mini
Agent Style=ReAct, Max...
2026.03
72.3
Qwen3.5-397B
Agent Style=ReAct, Max...
2026.03
70.3
Gemini-3.0-Pro
Agent Style=ReAct, Max...
2026.03
66.8
DeepSeek-V3.2
Agent Style=ReAct, Max...
2026.03
65
OpenAI-GPT-5
Agent Style=ReAct, Max...
2026.03
65
Claude-4.5-Opus
Agent Style=ReAct, Max...
2026.03
62.4
Tongyi-DeepResearch-30B
Agent Style=ReAct, Max...
2026.03
46.7
Feedback
Search any
task
Search any
task