List your company

Code Generation on MBPP (Perf., Cost)

84.26Performance (%)FlowBank
69.824873.572477.3281.0676Jun 9, 2026

Evaluation results

MethodLinks
FlowBankExecutor LLM=GPT-4o mini, Optimizer LLM=Qwen3-8B2026.0684.261.62
AFlow (GPT-4o)Executor LLM=GPT-4o mini, Optimizer LLM=GPT-4o2026.0683.770.57
ScoreFlowExecutor LLM=GPT-4o mini, Generator LLM=Qwen3-8B2026.0683.631.7
AFlow (Qwen3-8B)Executor LLM=GPT-4o mini, Optimizer LLM=Qwen3-8B2026.0679.371.02
MaASExecutor LLM=GPT-4o mini2026.0679.082.04
Multi-agent DebateExecutor LLM=GPT-4o mini2026.0674.680.86
CoTExecutor LLM=GPT-4o mini2026.0674.290.08
Self-ConsistencyExecutor LLM=GPT-4o mini2026.0673.980.52
IOExecutor LLM=GPT-4o mini2026.0672.920.08
AgentSquareExecutor LLM=GPT-4o mini, Optimizer LLM=GPT-4o2026.0672.730.52
ADASExecutor LLM=GPT-4o mini, Optimizer LLM=GPT-4o2026.0672.340.77
MedPromptExecutor LLM=GPT-4o mini2026.0671.850.61
ComplexCoTExecutor LLM=GPT-4o mini2026.0671.680.1
GPTSwarmExecutor LLM=GPT-4o mini2026.0671.260.25
Self-RefineExecutor LLM=GPT-4o mini2026.0671.070.27
MultiPersonaExecutor LLM=GPT-4o mini2026.0670.380.28