Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Collaborative software engineering on MultiAgentBench Coding (Tree)
Loading...
52.98
Task Performance
ETI
45.4608
47.4129
49.365
51.3171
Apr 21, 2026
Task Performance
Coordination
Updated 1mo ago
Evaluation Results
Method
Method
Links
Task Performance
Coordination
ETI
Agent=QWEN, Trait Sour...
2026.04
52.98
66.34
ETI
Agent=QWEN, Trait Sour...
2026.04
52.13
66.81
ETI
Agent=GPT, Trait Sourc...
2026.04
50.69
72.95
ETI
Agent=GPT, Trait Sourc...
2026.04
50.22
74.43
GPT
Trait Source=none
2026.04
45.79
52.22
QWEN
Trait Source=none
2026.04
45.75
60.41
Feedback
Search any
task
Search any
task