Claw-Eval
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
Claw-Eval
80.6Average Score
22
Claw-Eval general domain 0408
70.8Pass@3
13
Claw-Eval Continuous Mode v1 (test)
63.4Overall Performance
11
Claw-Eval Isolated Mode v1 (test)
64.5Overall Success Rate
11