List your company

Reading Comprehension on DROP (Performance and Cost)

83.49Performance ScoreFlowBank
75.1777.3379.4981.65Jun 9, 2026

Evaluation results

MethodLinks
FlowBankExecutor LLM=GPT-4o mini, Optimizer LLM=Qwen3-8B2026.0683.491.06
ScoreFlowExecutor LLM=GPT-4o mini, Generator LLM=Qwen3-8B2026.0682.11.42
MedPromptExecutor LLM=GPT-4o mini2026.0681.771.75
ADASExecutor LLM=GPT-4o mini, Optimizer LLM=GPT-4o2026.0681.170.98
AFlow (GPT-4o)Executor LLM=GPT-4o mini, Optimizer LLM=GPT-4o2026.0680.261.02
Multi-agent DebateExecutor LLM=GPT-4o mini2026.0678.651.64
GPTSwarmExecutor LLM=GPT-4o mini2026.0678.370.51
Self-ConsistencyExecutor LLM=GPT-4o mini2026.0678.330.74
CoTExecutor LLM=GPT-4o mini2026.0677.960.11
ComplexCoTExecutor LLM=GPT-4o mini2026.0677.740.33
AFlow (Qwen3-8B)Executor LLM=GPT-4o mini, Optimizer LLM=Qwen3-8B2026.0677.081.05
AgentSquareExecutor LLM=GPT-4o mini, Optimizer LLM=GPT-4o2026.0676.840.76
Self-RefineExecutor LLM=GPT-4o mini2026.0676.710.34
MaASExecutor LLM=GPT-4o mini2026.0676.641.64
MultiPersonaExecutor LLM=GPT-4o mini2026.0676.130.29
IOExecutor LLM=GPT-4o mini2026.0675.490.08