List your company

Question Answering on MMLU (EM and F1 Scores)

85EM ScoreAgent
71.4874.9978.582.01Jun 1, 2026

Evaluation results

MethodLinks
AgentBackbone=Qwen3-8B, Budget Strategy=Per-query Budget, B = 20, Avg. Cost=2.90, Avg. Psg=1.14, Avg. Steps=2.142026.068585
AgentBackbone=Qwen3-8B, Budget Strategy=Shared Budget, Avg. Cost=2.56, Avg. Psg=0.86, Avg. Steps=1.862026.068585
AgentBackbone=Llama3.1-8B-Instruct, Budget Strategy=Per-query Budget, B = 20, Avg. Cost=15.74, Avg. Psg=7.02, Avg. Steps=8.112026.067272
AgentBackbone=Llama3.1-8B-Instruct, Budget Strategy=Shared Budget, Avg. Cost=16.04, Avg. Psg=6.28, Avg. Steps=7.352026.067272