List your company

Reading Comprehension on DROP (Score)

0.6733DROP ScoreStar1
0.4474120.5060560.56470.623344Jun 15, 2026

Evaluation results

MethodLinks
Star1Backbone Model=DeepSeek-R1-Distill-Llama-70B2026.060.6733
ST-DBackbone Model=DeepSeek-R1-Distill-Llama-70B2026.060.673
BaseBackbone Model=DeepSeek-R1-Distill-Llama-70B2026.060.6721
ST-SBackbone Model=DeepSeek-R1-Distill-Llama-70B2026.060.6689
SafePathBackbone Model=DeepSeek-R1-Distill-Llama-70B2026.060.6665
BaseBackbone Model=Qwen3-8B2026.060.6623
ST-SBackbone Model=Qwen3-8B2026.060.658
ST-DBackbone Model=Qwen3-8B2026.060.6567
SafePathBackbone Model=Qwen3-32B2026.060.6513
Star1Backbone Model=Qwen3-32B2026.060.6402
Star1Backbone Model=Qwen3-8B2026.060.6364
BaseBackbone Model=Qwen3-32B2026.060.6272
SafePathBackbone Model=Qwen3-8B2026.060.6226
ST-SBackbone Model=Qwen3-32B2026.060.6081
ST-DBackbone Model=Qwen3-32B2026.060.6081
ST-SBackbone Model=DeepSeek-R1-Distill-Llama-8B2026.060.4876
Star1Backbone Model=DeepSeek-R1-Distill-Llama-8B2026.060.4837
BaseBackbone Model=DeepSeek-R1-Distill-Llama-8B2026.060.4677
ST-DBackbone Model=DeepSeek-R1-Distill-Llama-8B2026.060.462
SafePathBackbone Model=DeepSeek-R1-Distill-Llama-8B2026.060.4561