Code Generation on LiveCodeBench V4 (test)
46.3pass@1AgentConductor
Evaluation Results
| Method | Links | |
|---|---|---|
| AgentConductorSystem Category=Multi-Agent Systems with Topology Optimization, Model Scale=3B2026.02 | 46.3 | |
| Chain-of-AgentsSystem Category=Multi-Agent Systems with Workflow Optimization, Model Scale=32B2026.02 | 44.9 | |
| FlowReasonerSystem Category=Multi-Agent Systems with Workflow Optimization2026.02 | 43.8 | |
| MetaGPTSystem Category=Classical Multi-Agent Systems2026.02 | 42.8 | |
| AgentPruneSystem Category=Multi-Agent Systems with Topology Optimization, Topology Variant=Layered2026.02 | 41.9 | |
| AgentPruneSystem Category=Multi-Agent Systems with Topology Optimization, Topology Variant=Complex2026.02 | 41.7 | |
| GPTSwarmSystem Category=Multi-Agent Systems with Topology Optimization2026.02 | 40.8 | |
| MacNetSystem Category=Multi-Agent Systems with Topology Optimization, Topology Variant=Layered2026.02 | 40.3 | |
| MacNetSystem Category=Multi-Agent Systems with Topology Optimization, Topology Variant=Complex2026.02 | 39.4 | |
| G-DesignerSystem Category=Multi-Agent Systems with Topology Optimization2026.02 | 38.8 | |
| MapCoderSystem Category=Classical Multi-Agent Systems2026.02 | 37.4 | |
| AutoGenSystem Category=Classical Multi-Agent Systems2026.02 | 30.2 | |
| GPT-4o-miniSystem Category=Vanilla, Backbone=GPT-4o-mini2026.02 | 26.3 | |
| AFlowSystem Category=Multi-Agent Systems with Workflow Optimization2026.02 | 24.6 |