List your company

Knowledge Intensive on Gaokao History

83AccuracyMemAPO
52.11260.13168.1576.169Mar 23, 2026

Evaluation results

MethodLinks
MemAPOBackbone=Qwen3-8B2026.0383
PromptBreederBackbone=Qwen3-8B2026.0381.5
ProTeGiBackbone=Qwen3-8B2026.0380.7
IOBackbone=Qwen3-8B2026.0380
TextGradBackbone=Qwen3-8B2026.0379.3
CoTBackbone=Qwen3-8B2026.0378.5
SPOBackbone=Qwen3-8B2026.0378.5
RaRBackbone=Qwen3-8B2026.0377.8
OPROBackbone=Qwen3-8B2026.0377
Step-BackBackbone=Qwen3-8B2026.0376.3
MemAPOBackbone=GPT-4o-mini2026.0372.6
TextGradBackbone=GPT-4o-mini2026.0372.6
MemAPOBackbone=GPT-4o-mini2026.0372.6
IOBackbone=GPT-4o-mini2026.0371.9
SPOBackbone=GPT-4o-mini2026.0371.9
IOBackbone=GPT-4o-mini2026.0371.9
PromptBreederBackbone=GPT-4o-mini2026.0371.1
SPOBackbone=GPT-4o-mini2026.0370.4
TextGradBackbone=GPT-4o-mini2026.0369.6
OPROBackbone=GPT-4o-mini2026.0368.1
CoTBackbone=GPT-4o-mini2026.0367.4
OPROBackbone=GPT-4o-mini2026.0367.4
CoTBackbone=GPT-4o-mini2026.0367.4
PromptBreederBackbone=GPT-4o-mini2026.0365.9
StepBackBackbone=GPT-4o-mini2026.0360.7
Step-BackBackbone=GPT-4o-mini2026.0360.7
ProTeGiBackbone=GPT-4o-mini2026.0360
RephraseBackbone=GPT-4o-mini2026.0358.5
RaRBackbone=GPT-4o-mini2026.0358.5
ProTeGiBackbone=GPT-4o-mini2026.0353.3