List your company

Performance Shift Prediction on MMLU-Pro

0.8R-squaredSTS_act
0.34240.46120.580.6988Mar 3, 2026

Evaluation results

MethodLinks
STS_actModel=Qwen2.5-7B, SFT Dataset=LIMO2026.030.8
STS_ICLModel=LLaMA3-8B, SFT Dataset=LIMO2026.030.66
STS_ICLModel=Qwen2.5-7B, SFT Dataset=LIMO2026.030.61
STS_ICLModel=Gemma2-9B, SFT Dataset=LIMO2026.030.6
STS_actModel=LLaMA3-8B, SFT Dataset=LIMO2026.030.5
STS_actModel=Gemma2-9B, SFT Dataset=LIMO2026.030.36