Reasoning
195 tasks
Best: AnyGen
Tool-Use
180 tasks
Best: AnyGen
Memory
30 tasks
Best: AnyGen
Multimodal
25 tasks
Best: AnyGen
Collaboration
30 tasks
Best: AnyGen
FrameworkReasoningTool-UseMemoryMultimodalCollaborationAvg
AnyGen100.00100.00100.00100.00100.00100.00
Claude Code100.0091.0087.5088.0084.0090.10
CodeBuddy100.00100.00100.00100.00100.00100.00
H.O.P.E.100.00100.00100.00100.00100.00100.00
Manus100.0091.0087.5088.0084.0090.10
OpenClaw100.00100.00100.00100.00100.00100.00
OpenClaw (Miaoda)100.00100.00100.00100.00100.00100.00
WorkBuddy100.0091.0087.5088.0084.0090.10
Hermes Agent73.7383.2084.2272.1885.0079.67

Capability Profiles

AnyGen
Reasoning
100.00
Tool-Use
100.00
Memory
100.00
Multimodal
100.00
Collaboration
100.00
Claude Code
Reasoning
100.00
Tool-Use
91.00
Memory
87.50
Multimodal
88.00
Collaboration
84.00
CodeBuddy
Reasoning
100.00
Tool-Use
100.00
Memory
100.00
Multimodal
100.00
Collaboration
100.00
H.O.P.E.
Reasoning
100.00
Tool-Use
100.00
Memory
100.00
Multimodal
100.00
Collaboration
100.00