Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Deep Search Question Answering on Deep SearchQA
Loading...
80
Score
Claude-4.5-Opus
15.312
32.106
48.9
65.694
Mar 30, 2026
Score
Updated 18d ago
Evaluation Results
Method
Method
Links
Score
Claude-4.5-Opus
Model Category=Foundat...
2026.03
80
OpenAI GPT-5 High
Model Category=Foundat...
2026.03
79
Kimi-K2.5
Model Category=Foundat...
2026.03
77.1
Gemini-3.0-Pro
Model Category=Foundat...
2026.03
76.9
MiroThinker-v1.7-mini
Model Category=Trained...
2026.03
67.9
DeepSeek-V3.2
Model Category=Foundat...
2026.03
60.9
MiroThinker-v1.0-8B
Model Category=Trained...
2026.03
36.7
AgentCPM-Explore-4B
Model Category=Trained...
2026.03
32.8
Marco-DR-8B
Model Category=Trained...
2026.03
29.2
WebExplorer-8B-RL
Model Category=Trained...
2026.03
17.8
Feedback
Search any
task
Search any
task