Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Deep Information Retrieval and Research on xbench DeepSearch
Loading...
77.8
Avg@8
OpenAI-GPT-5-high
52.736
59.243
65.75
72.257
Nov 14, 2025
Avg@8
Updated 1mo ago
Evaluation Results
Method
Method
Links
Avg@8
OpenAI-GPT-5-high
Type=Foundation Models...
2025.11
77.8
MiroThinker-v1.0-72B
Parameters=72B
2025.11
77.8
Tongyi-DeepResearch-30B
Type=Research Agents
2025.11
75
Minimax-M2
Type=Foundation Models...
2025.11
72
DeepSeek-V3.1
Type=Foundation Models...
2025.11
71
DeepSeek-V3.2
Type=Foundation Models...
2025.11
71
MiroThinker-v1.0-30B
Parameters=30B
2025.11
70.6
GLM-4.6
Type=Foundation Models...
2025.11
70
Kimi-Researcher
Type=Research Agents
2025.11
69
OpenAI-o3
Type=Foundation Models...
2025.11
67
Claude-4.5-Sonnet
Type=Foundation Models...
2025.11
66
Claude-4-Sonnet
Type=Foundation Models...
2025.11
64.6
DeepMiner-32B-RL
Type=Research Agents
2025.11
62
Kimi-K2-0905
Type=Foundation Models...
2025.11
61
MiroThinker-v1.0-8B
Parameters=8B
2025.11
60.6
WebExplorer-8B-RL
Type=Research Agents
2025.11
53.7
Feedback
Search any
task
Search any
task