Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Web Browsing and Navigation on BrowseComp
Loading...
68.9
Avg@3 Score
ChatGPT-Agent
4.94
21.545
38.15
54.755
Nov 14, 2025
Avg@3 Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Avg@3 Score
ChatGPT-Agent
Type=Research Agents
2025.11
68.9
OpenAI-GPT-5-high
Type=Foundation Models...
2025.11
54.9
OpenAI DeepResearch
Type=Research Agents
2025.11
51.5
OpenAI-o3
Type=Foundation Models...
2025.11
49.7
MiroThinker-v1.0-72B
Parameters=72B
2025.11
47.1
GLM-4.6
Type=Foundation Models...
2025.11
45.1
Minimax-M2
Type=Foundation Models...
2025.11
44
Tongyi-DeepResearch-30B
Type=Research Agents
2025.11
43.4
MiroThinker-v1.0-30B
Parameters=30B
2025.11
41.2
DeepSeek-V3.2
Type=Foundation Models...
2025.11
40.1
DeepMiner-32B-RL
Type=Research Agents
2025.11
33.5
MiroThinker-v1.0-8B
Parameters=8B
2025.11
31.1
DeepSeek-V3.1
Type=Foundation Models...
2025.11
30
Claude-4.5-Sonnet
Type=Foundation Models...
2025.11
19.6
WebExplorer-8B-RL
Type=Research Agents
2025.11
15.7
Claude-4-Sonnet
Type=Foundation Models...
2025.11
12.2
AFM-32B-RL
Type=Research Agents
2025.11
11.1
Kimi-K2-0905
Type=Foundation Models...
2025.11
7.4
Feedback
Search any
task
Search any
task