List your company

Question Answering and Reasoning on ARC Mean of Easy and Challenge

94.75AccuracyST-D
86.669288.767190.86592.9629Jun 15, 2026

Evaluation results

MethodLinks
ST-DBackbone Model=Qwen3-32B2026.0694.75
ST-SBackbone Model=Qwen3-32B2026.0694.61
BaseBackbone Model=Qwen3-32B2026.0694.59
SafePathBackbone Model=Qwen3-32B2026.0694.59
Star1Backbone Model=Qwen3-32B2026.0694.34
Star1Backbone Model=DeepSeek-R1-Distill-Llama-70B2026.0694.33
ST-DBackbone Model=DeepSeek-R1-Distill-Llama-70B2026.0694.17
BaseBackbone Model=DeepSeek-R1-Distill-Llama-70B2026.0694.16
SafePathBackbone Model=DeepSeek-R1-Distill-Llama-70B2026.0694.11
ST-SBackbone Model=DeepSeek-R1-Distill-Llama-70B2026.0694.11
Star1Backbone Model=Qwen3-8B2026.0692.78
BaseBackbone Model=Qwen3-8B2026.0692.67
SafePathBackbone Model=Qwen3-8B2026.0692.64
ST-SBackbone Model=Qwen3-8B2026.0692.5
ST-DBackbone Model=Qwen3-8B2026.0692.42
BaseBackbone Model=DeepSeek-R1-Distill-Llama-8B2026.0688.1
Star1Backbone Model=DeepSeek-R1-Distill-Llama-8B2026.0687.96
ST-DBackbone Model=DeepSeek-R1-Distill-Llama-8B2026.0687.91
ST-SBackbone Model=DeepSeek-R1-Distill-Llama-8B2026.0687.49
SafePathBackbone Model=DeepSeek-R1-Distill-Llama-8B2026.0686.98