Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Collaborative software engineering on MultiAgentBench Coding Graph

57.41Task Performance

QWEN

50.96252.63654.3155.984Apr 21, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.04
57.4174.29
2026.04
56.8286.46
2026.04
56.4484.43
2026.04
53.3173.52
2026.04
52.8474.38
2026.04
51.2157.01