Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Web Browsing and Navigation (Chinese) on BrowseComp-ZH
Loading...
65
Avg@3
OpenAI-GPT-5-high
20.488
32.044
43.6
55.156
Nov 14, 2025
Avg@3
Updated 1mo ago
Evaluation Results
Method
Method
Links
Avg@3
OpenAI-GPT-5-high
Type=Foundation Models...
2025.11
65
OpenAI-o3
Type=Foundation Models...
2025.11
58.1
MiroThinker-v1.0-72B
Parameters=72B
2025.11
55.6
GLM-4.6
Type=Foundation Models...
2025.11
49.5
DeepSeek-V3.1
Type=Foundation Models...
2025.11
49.2
Minimax-M2
Type=Foundation Models...
2025.11
48.5
DeepSeek-V3.2
Type=Foundation Models...
2025.11
47.9
MiroThinker-v1.0-30B
Parameters=30B
2025.11
47.8
Tongyi-DeepResearch-30B
Type=Research Agents
2025.11
46.7
OpenAI DeepResearch
Type=Research Agents
2025.11
42.9
Claude-4.5-Sonnet
Type=Foundation Models...
2025.11
40.8
MiroThinker-v1.0-8B
Parameters=8B
2025.11
40.2
DeepMiner-32B-RL
Type=Research Agents
2025.11
40.1
WebExplorer-8B-RL
Type=Research Agents
2025.11
32
Claude-4-Sonnet
Type=Foundation Models...
2025.11
29.1
Kimi-K2-0905
Type=Foundation Models...
2025.11
22.2
Feedback
Search any
task
Search any
task