List your company
ResearchFormerly WizWand

Aggregated Multi-task Evaluation on Average

73.4Performance ScoreFlowBank
57.342461.511265.6869.8488Jun 9, 2026
Updated 4mo ago

Evaluation results

MethodLinks
FlowBankExecutor LLM=GPT-4o mini, Optimizer LLM=Qwen3-8B2026.0673.41.65
AFlow (GPT-4o)Executor LLM=GPT-4o mini, Optimizer LLM=GPT-4o2026.0670.41.95
ScoreFlowExecutor LLM=GPT-4o mini, Generator LLM=Qwen3-8B2026.0669.512.37
AFlow (Qwen3-8B)Executor LLM=GPT-4o mini, Optimizer LLM=Qwen3-8B2026.0668.561.79
MaASExecutor LLM=GPT-4o mini2026.0668.091.9
AgentSquareExecutor LLM=GPT-4o mini, Optimizer LLM=GPT-4o2026.0666.71.02
MultiPersonaExecutor LLM=GPT-4o mini2026.0663.870.41
Multi-agent DebateExecutor LLM=GPT-4o mini2026.0663.863.45
ComplexCoTExecutor LLM=GPT-4o mini2026.0663.850.42
GPTSwarmExecutor LLM=GPT-4o mini2026.0663.432.54
ADASExecutor LLM=GPT-4o mini, Optimizer LLM=GPT-4o2026.0663.221.71
MedPromptExecutor LLM=GPT-4o mini2026.0662.772.58
Self-ConsistencyExecutor LLM=GPT-4o mini2026.0661.491.51
CoTExecutor LLM=GPT-4o mini2026.0660.980.23
IOExecutor LLM=GPT-4o mini2026.0660.440.22
Self-RefineExecutor LLM=GPT-4o mini2026.0657.960.62