141 lines
4.5 KiB
Plaintext
141 lines
4.5 KiB
Plaintext
beam_1M_4_abstention_q0
|
|
beam_1M_4_abstention_q1
|
|
beam_1M_4_contradiction_resolution_q0
|
|
beam_1M_4_contradiction_resolution_q1
|
|
beam_1M_4_event_ordering_q0
|
|
beam_1M_4_event_ordering_q1
|
|
beam_1M_4_information_extraction_q0
|
|
beam_1M_4_information_extraction_q1
|
|
beam_1M_4_instruction_following_q0
|
|
beam_1M_4_instruction_following_q1
|
|
beam_1M_4_knowledge_update_q0
|
|
beam_1M_4_knowledge_update_q1
|
|
beam_1M_4_multi_session_reasoning_q0
|
|
beam_1M_4_multi_session_reasoning_q1
|
|
beam_1M_4_preference_following_q0
|
|
beam_1M_4_preference_following_q1
|
|
beam_1M_4_summarization_q0
|
|
beam_1M_4_summarization_q1
|
|
beam_1M_4_temporal_reasoning_q0
|
|
beam_1M_4_temporal_reasoning_q1
|
|
beam_1M_5_abstention_q0
|
|
beam_1M_5_abstention_q1
|
|
beam_1M_5_contradiction_resolution_q0
|
|
beam_1M_5_contradiction_resolution_q1
|
|
beam_1M_5_event_ordering_q0
|
|
beam_1M_5_event_ordering_q1
|
|
beam_1M_5_information_extraction_q0
|
|
beam_1M_5_information_extraction_q1
|
|
beam_1M_5_instruction_following_q0
|
|
beam_1M_5_instruction_following_q1
|
|
beam_1M_5_knowledge_update_q0
|
|
beam_1M_5_knowledge_update_q1
|
|
beam_1M_5_multi_session_reasoning_q0
|
|
beam_1M_5_multi_session_reasoning_q1
|
|
beam_1M_5_preference_following_q0
|
|
beam_1M_5_preference_following_q1
|
|
beam_1M_5_summarization_q0
|
|
beam_1M_5_summarization_q1
|
|
beam_1M_5_temporal_reasoning_q0
|
|
beam_1M_5_temporal_reasoning_q1
|
|
beam_1M_11_abstention_q0
|
|
beam_1M_11_abstention_q1
|
|
beam_1M_11_contradiction_resolution_q0
|
|
beam_1M_11_contradiction_resolution_q1
|
|
beam_1M_11_event_ordering_q0
|
|
beam_1M_11_event_ordering_q1
|
|
beam_1M_11_information_extraction_q0
|
|
beam_1M_11_information_extraction_q1
|
|
beam_1M_11_instruction_following_q0
|
|
beam_1M_11_instruction_following_q1
|
|
beam_1M_11_knowledge_update_q0
|
|
beam_1M_11_knowledge_update_q1
|
|
beam_1M_11_multi_session_reasoning_q0
|
|
beam_1M_11_multi_session_reasoning_q1
|
|
beam_1M_11_preference_following_q0
|
|
beam_1M_11_preference_following_q1
|
|
beam_1M_11_summarization_q0
|
|
beam_1M_11_summarization_q1
|
|
beam_1M_11_temporal_reasoning_q0
|
|
beam_1M_11_temporal_reasoning_q1
|
|
beam_1M_14_abstention_q0
|
|
beam_1M_14_abstention_q1
|
|
beam_1M_14_contradiction_resolution_q0
|
|
beam_1M_14_contradiction_resolution_q1
|
|
beam_1M_14_event_ordering_q0
|
|
beam_1M_14_event_ordering_q1
|
|
beam_1M_14_information_extraction_q0
|
|
beam_1M_14_information_extraction_q1
|
|
beam_1M_14_instruction_following_q0
|
|
beam_1M_14_instruction_following_q1
|
|
beam_1M_14_knowledge_update_q0
|
|
beam_1M_14_knowledge_update_q1
|
|
beam_1M_14_multi_session_reasoning_q0
|
|
beam_1M_14_multi_session_reasoning_q1
|
|
beam_1M_14_preference_following_q0
|
|
beam_1M_14_preference_following_q1
|
|
beam_1M_14_summarization_q0
|
|
beam_1M_14_summarization_q1
|
|
beam_1M_14_temporal_reasoning_q0
|
|
beam_1M_14_temporal_reasoning_q1
|
|
beam_1M_17_abstention_q0
|
|
beam_1M_17_abstention_q1
|
|
beam_1M_17_contradiction_resolution_q0
|
|
beam_1M_17_contradiction_resolution_q1
|
|
beam_1M_17_event_ordering_q0
|
|
beam_1M_17_event_ordering_q1
|
|
beam_1M_17_information_extraction_q0
|
|
beam_1M_17_information_extraction_q1
|
|
beam_1M_17_instruction_following_q0
|
|
beam_1M_17_instruction_following_q1
|
|
beam_1M_17_knowledge_update_q0
|
|
beam_1M_17_knowledge_update_q1
|
|
beam_1M_17_multi_session_reasoning_q0
|
|
beam_1M_17_multi_session_reasoning_q1
|
|
beam_1M_17_preference_following_q0
|
|
beam_1M_17_preference_following_q1
|
|
beam_1M_17_summarization_q0
|
|
beam_1M_17_summarization_q1
|
|
beam_1M_17_temporal_reasoning_q0
|
|
beam_1M_17_temporal_reasoning_q1
|
|
beam_1M_18_abstention_q0
|
|
beam_1M_18_abstention_q1
|
|
beam_1M_18_contradiction_resolution_q0
|
|
beam_1M_18_contradiction_resolution_q1
|
|
beam_1M_18_event_ordering_q0
|
|
beam_1M_18_event_ordering_q1
|
|
beam_1M_18_information_extraction_q0
|
|
beam_1M_18_information_extraction_q1
|
|
beam_1M_18_instruction_following_q0
|
|
beam_1M_18_instruction_following_q1
|
|
beam_1M_18_knowledge_update_q0
|
|
beam_1M_18_knowledge_update_q1
|
|
beam_1M_18_multi_session_reasoning_q0
|
|
beam_1M_18_multi_session_reasoning_q1
|
|
beam_1M_18_preference_following_q0
|
|
beam_1M_18_preference_following_q1
|
|
beam_1M_18_summarization_q0
|
|
beam_1M_18_summarization_q1
|
|
beam_1M_18_temporal_reasoning_q0
|
|
beam_1M_18_temporal_reasoning_q1
|
|
beam_1M_28_abstention_q0
|
|
beam_1M_28_abstention_q1
|
|
beam_1M_28_contradiction_resolution_q0
|
|
beam_1M_28_contradiction_resolution_q1
|
|
beam_1M_28_event_ordering_q0
|
|
beam_1M_28_event_ordering_q1
|
|
beam_1M_28_information_extraction_q0
|
|
beam_1M_28_information_extraction_q1
|
|
beam_1M_28_instruction_following_q0
|
|
beam_1M_28_instruction_following_q1
|
|
beam_1M_28_knowledge_update_q0
|
|
beam_1M_28_knowledge_update_q1
|
|
beam_1M_28_multi_session_reasoning_q0
|
|
beam_1M_28_multi_session_reasoning_q1
|
|
beam_1M_28_preference_following_q0
|
|
beam_1M_28_preference_following_q1
|
|
beam_1M_28_summarization_q0
|
|
beam_1M_28_summarization_q1
|
|
beam_1M_28_temporal_reasoning_q0
|
|
beam_1M_28_temporal_reasoning_q1
|