Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Deep research on MCP-Bench-Wiki
Loading...
60.01
Mean@3
AdaCoM
43.7236
47.9518
52.18
56.4082
May 29, 2026
Mean@3
Updated 2d ago
Evaluation Results
Method
Method
Links
Mean@3
AdaCoM
Agent=Kimi-K2-Instruct
2026.05
60.01
AdaCoM
Agent=Avg.
2026.05
59.05
AdaCoM
Agent=DeepSeek-V3
2026.05
58.09
ReAct
Agent=Kimi-K2-Instruct
2026.05
55.05
ReAct
Agent=Avg.
2026.05
51.28
AdaCoM w/o train.
Agent=DeepSeek-V3
2026.05
47.82
ReAct
Agent=DeepSeek-V3
2026.05
47.51
AdaCoM w/o train.
Agent=Avg.
2026.05
46.09
AdaCoM w/o train.
Agent=Kimi-K2-Instruct
2026.05
44.35
Feedback
Search any
task
Search any
task