3-agent
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
3-agent Sum (evaluation set)
51.67Valid Rate
7
3-agent 10x10 (test)
32Valid Rate
7
3-agent 9x9 (test)
44Valid Rate
7
3-agent 8x8 (test)
42.67Valid Rate
7
3-agent 7x7 (evaluation)
46Valid Rate
7
3-agent 6x6 (evaluation set)
52.67Valid Rate
7
3-agent 5x5 (evaluation set)
62.67Valid Rate
7
3-agent 4x4 (test)
64.67Valid Rate
7