List your company

Multi-hop Question Answering on HotpotQA tool-augmented 1 (test)

72.8EMFLOWBOT
36.60846.00455.464.796Apr 29, 2026

Evaluation results

MethodLinks
FLOWBOTModel=GPT-4.1 mini2026.0472.8
GEPAModel=GPT-4.1 mini2026.0469
GEPA+MergeModel=GPT-4.1 mini2026.0465.67
TextGradModel=GPT-4.1 mini2026.0462.33
TraceModel=GPT-4.1 mini2026.0460.33
MIPROv2Model=GPT-4.1 mini2026.0458
BaselineModel=GPT-4.1 mini2026.0438