![[ICO]](/icons/blank.gif) | Name | Last modified | Size | Description |
|---|
|
|---|
![[DIR]](/icons/back.gif) | Parent Directory | | - | |
![[DIR]](/icons/folder.gif) | eval_cache/ | 17-Jul-2024 20:03 | - | |
| gsm:model=mistralai_open-mistral-nemo-2407/ | 23-Jul-2024 15:00 | - | |
| commonsense:dataset=openbookqa,method=multiple_choice_joint,model=mistralai_open-mistral-nemo-2407/ | 23-Jul-2024 15:00 | - | |
| commonsense:dataset=openbookqa,method=multiple_choice_joint,model=openai_gpt-4o-mini-2024-07-18/ | 23-Jul-2024 15:00 | - | |
| gsm:model=openai_gpt-4o-mini-2024-07-18/ | 23-Jul-2024 15:00 | - | |
| commonsense:dataset=openbookqa,method=multiple_choice_joint,model=microsoft_phi-3-small-8k-instruct/ | 23-Jul-2024 15:00 | - | |
| commonsense:dataset=openbookqa,method=multiple_choice_joint,model=microsoft_phi-3-medium-4k-instruct/ | 23-Jul-2024 15:00 | - | |
| gsm:model=microsoft_phi-3-medium-4k-instruct/ | 23-Jul-2024 15:00 | - | |
| legalbench:subset=abercrombie,model=microsoft_phi-3-medium-4k-instruct/ | 23-Jul-2024 15:00 | - | |
| gsm:model=microsoft_phi-3-small-8k-instruct/ | 23-Jul-2024 15:00 | - | |
| legalbench:subset=abercrombie,model=microsoft_phi-3-small-8k-instruct/ | 23-Jul-2024 15:00 | - | |
| legalbench:subset=abercrombie,model=openai_gpt-4o-mini-2024-07-18/ | 23-Jul-2024 15:00 | - | |
| legalbench:subset=abercrombie,model=mistralai_open-mistral-nemo-2407/ | 23-Jul-2024 15:00 | - | |
| legalbench:subset=corporate_lobbying,model=microsoft_phi-3-medium-4k-instruct/ | 23-Jul-2024 15:00 | - | |
| legalbench:subset=corporate_lobbying,model=microsoft_phi-3-small-8k-instruct/ | 23-Jul-2024 15:00 | - | |
| legalbench:subset=corporate_lobbying,model=mistralai_open-mistral-nemo-2407/ | 23-Jul-2024 15:00 | - | |
| legalbench:subset=corporate_lobbying,model=openai_gpt-4o-mini-2024-07-18/ | 23-Jul-2024 15:00 | - | |
| legalbench:subset=function_of_decision_section,model=openai_gpt-4o-mini-2024-07-18/ | 23-Jul-2024 15:00 | - | |
| legalbench:subset=function_of_decision_section,model=mistralai_open-mistral-nemo-2407/ | 23-Jul-2024 15:00 | - | |
| legalbench:subset=function_of_decision_section,model=microsoft_phi-3-medium-4k-instruct/ | 23-Jul-2024 15:00 | - | |
| legalbench:subset=function_of_decision_section,model=microsoft_phi-3-small-8k-instruct/ | 23-Jul-2024 15:00 | - | |
| legalbench:subset=international_citizenship_questions,model=microsoft_phi-3-medium-4k-instruct/ | 23-Jul-2024 15:00 | - | |
| legalbench:subset=international_citizenship_questions,model=mistralai_open-mistral-nemo-2407/ | 23-Jul-2024 15:00 | - | |
| legalbench:subset=international_citizenship_questions,model=microsoft_phi-3-small-8k-instruct/ | 23-Jul-2024 15:00 | - | |
| legalbench:subset=proa,model=openai_gpt-4o-mini-2024-07-18/ | 23-Jul-2024 15:00 | - | |
| legalbench:subset=proa,model=microsoft_phi-3-medium-4k-instruct/ | 23-Jul-2024 15:00 | - | |
| legalbench:subset=international_citizenship_questions,model=openai_gpt-4o-mini-2024-07-18/ | 23-Jul-2024 15:00 | - | |
| legalbench:subset=proa,model=mistralai_open-mistral-nemo-2407/ | 23-Jul-2024 15:00 | - | |
| legalbench:subset=proa,model=microsoft_phi-3-small-8k-instruct/ | 23-Jul-2024 15:00 | - | |
| math:subject=algebra,level=1,use_official_examples=False,use_chain_of_thought=True,model=microsoft_phi-3-small-8k-instruct/ | 23-Jul-2024 15:00 | - | |
| math:subject=algebra,level=1,use_official_examples=False,use_chain_of_thought=True,model=mistralai_open-mistral-nemo-2407/ | 23-Jul-2024 15:00 | - | |
| math:subject=algebra,level=1,use_official_examples=False,use_chain_of_thought=True,model=microsoft_phi-3-medium-4k-instruct/ | 23-Jul-2024 15:00 | - | |
| math:subject=algebra,level=1,use_official_examples=False,use_chain_of_thought=True,model=openai_gpt-4o-mini-2024-07-18/ | 23-Jul-2024 15:00 | - | |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=mistralai_open-mistral-nemo-2407/ | 23-Jul-2024 15:00 | - | |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=microsoft_phi-3-small-8k-instruct/ | 23-Jul-2024 15:00 | - | |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=microsoft_phi-3-medium-4k-instruct/ | 23-Jul-2024 15:00 | - | |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=openai_gpt-4o-mini-2024-07-18/ | 23-Jul-2024 15:00 | - | |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=mistralai_open-mistral-nemo-2407/ | 23-Jul-2024 15:00 | - | |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=microsoft_phi-3-small-8k-instruct/ | 23-Jul-2024 15:00 | - | |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=microsoft_phi-3-medium-4k-instruct/ | 23-Jul-2024 15:00 | - | |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=openai_gpt-4o-mini-2024-07-18/ | 23-Jul-2024 15:00 | - | |
| math:subject=intermediate_algebra,level=1,use_official_examples=False,use_chain_of_thought=True,model=mistralai_open-mistral-nemo-2407/ | 23-Jul-2024 15:00 | - | |
| math:subject=intermediate_algebra,level=1,use_official_examples=False,use_chain_of_thought=True,model=microsoft_phi-3-medium-4k-instruct/ | 23-Jul-2024 15:00 | - | |
| math:subject=intermediate_algebra,level=1,use_official_examples=False,use_chain_of_thought=True,model=microsoft_phi-3-small-8k-instruct/ | 23-Jul-2024 15:00 | - | |
| math:subject=intermediate_algebra,level=1,use_official_examples=False,use_chain_of_thought=True,model=openai_gpt-4o-mini-2024-07-18/ | 23-Jul-2024 15:00 | - | |
| math:subject=number_theory,level=1,use_official_examples=False,use_chain_of_thought=True,model=microsoft_phi-3-medium-4k-instruct/ | 23-Jul-2024 15:00 | - | |
| math:subject=number_theory,level=1,use_official_examples=False,use_chain_of_thought=True,model=microsoft_phi-3-small-8k-instruct/ | 23-Jul-2024 15:00 | - | |
| math:subject=number_theory,level=1,use_official_examples=False,use_chain_of_thought=True,model=mistralai_open-mistral-nemo-2407/ | 23-Jul-2024 15:00 | - | |
| math:subject=number_theory,level=1,use_official_examples=False,use_chain_of_thought=True,model=openai_gpt-4o-mini-2024-07-18/ | 23-Jul-2024 15:00 | - | |
| math:subject=prealgebra,level=1,use_official_examples=False,use_chain_of_thought=True,model=openai_gpt-4o-mini-2024-07-18/ | 23-Jul-2024 15:00 | - | |
| math:subject=prealgebra,level=1,use_official_examples=False,use_chain_of_thought=True,model=microsoft_phi-3-small-8k-instruct/ | 23-Jul-2024 15:00 | - | |
| math:subject=prealgebra,level=1,use_official_examples=False,use_chain_of_thought=True,model=microsoft_phi-3-medium-4k-instruct/ | 23-Jul-2024 15:00 | - | |
| math:subject=prealgebra,level=1,use_official_examples=False,use_chain_of_thought=True,model=mistralai_open-mistral-nemo-2407/ | 23-Jul-2024 15:00 | - | |
| math:subject=precalculus,level=1,use_official_examples=False,use_chain_of_thought=True,model=microsoft_phi-3-medium-4k-instruct/ | 23-Jul-2024 15:00 | - | |
| math:subject=precalculus,level=1,use_official_examples=False,use_chain_of_thought=True,model=mistralai_open-mistral-nemo-2407/ | 23-Jul-2024 15:00 | - | |
| math:subject=precalculus,level=1,use_official_examples=False,use_chain_of_thought=True,model=microsoft_phi-3-small-8k-instruct/ | 23-Jul-2024 15:00 | - | |
| math:subject=precalculus,level=1,use_official_examples=False,use_chain_of_thought=True,model=openai_gpt-4o-mini-2024-07-18/ | 23-Jul-2024 15:00 | - | |
| med_qa:model=mistralai_open-mistral-nemo-2407/ | 23-Jul-2024 15:00 | - | |
| med_qa:model=microsoft_phi-3-small-8k-instruct/ | 23-Jul-2024 15:00 | - | |
| med_qa:model=microsoft_phi-3-medium-4k-instruct/ | 23-Jul-2024 15:00 | - | |
| mmlu:subject=abstract_algebra,method=multiple_choice_joint,model=microsoft_phi-3-medium-4k-instruct/ | 23-Jul-2024 15:00 | - | |
| med_qa:model=openai_gpt-4o-mini-2024-07-18/ | 23-Jul-2024 15:00 | - | |
| mmlu:subject=abstract_algebra,method=multiple_choice_joint,model=microsoft_phi-3-small-8k-instruct/ | 23-Jul-2024 15:00 | - | |
| mmlu:subject=abstract_algebra,method=multiple_choice_joint,model=mistralai_open-mistral-nemo-2407/ | 23-Jul-2024 15:00 | - | |
| mmlu:subject=abstract_algebra,method=multiple_choice_joint,model=openai_gpt-4o-mini-2024-07-18/ | 23-Jul-2024 15:00 | - | |
| mmlu:subject=college_chemistry,method=multiple_choice_joint,model=microsoft_phi-3-medium-4k-instruct/ | 23-Jul-2024 15:00 | - | |
| mmlu:subject=college_chemistry,method=multiple_choice_joint,model=mistralai_open-mistral-nemo-2407/ | 23-Jul-2024 15:00 | - | |
| mmlu:subject=college_chemistry,method=multiple_choice_joint,model=openai_gpt-4o-mini-2024-07-18/ | 23-Jul-2024 15:00 | - | |
| mmlu:subject=college_chemistry,method=multiple_choice_joint,model=microsoft_phi-3-small-8k-instruct/ | 23-Jul-2024 15:00 | - | |
| mmlu:subject=computer_security,method=multiple_choice_joint,model=microsoft_phi-3-medium-4k-instruct/ | 23-Jul-2024 15:00 | - | |
| mmlu:subject=computer_security,method=multiple_choice_joint,model=mistralai_open-mistral-nemo-2407/ | 23-Jul-2024 15:00 | - | |
| mmlu:subject=computer_security,method=multiple_choice_joint,model=microsoft_phi-3-small-8k-instruct/ | 23-Jul-2024 15:00 | - | |
| mmlu:subject=computer_security,method=multiple_choice_joint,model=openai_gpt-4o-mini-2024-07-18/ | 23-Jul-2024 15:00 | - | |
| mmlu:subject=econometrics,method=multiple_choice_joint,model=microsoft_phi-3-small-8k-instruct/ | 23-Jul-2024 15:00 | - | |
| mmlu:subject=econometrics,method=multiple_choice_joint,model=mistralai_open-mistral-nemo-2407/ | 23-Jul-2024 15:00 | - | |
| mmlu:subject=econometrics,method=multiple_choice_joint,model=openai_gpt-4o-mini-2024-07-18/ | 23-Jul-2024 15:00 | - | |
| mmlu:subject=us_foreign_policy,method=multiple_choice_joint,model=mistralai_open-mistral-nemo-2407/ | 23-Jul-2024 15:00 | - | |
| mmlu:subject=econometrics,method=multiple_choice_joint,model=microsoft_phi-3-medium-4k-instruct/ | 23-Jul-2024 15:00 | - | |
| mmlu:subject=us_foreign_policy,method=multiple_choice_joint,model=microsoft_phi-3-small-8k-instruct/ | 23-Jul-2024 15:00 | - | |
| mmlu:subject=us_foreign_policy,method=multiple_choice_joint,model=microsoft_phi-3-medium-4k-instruct/ | 23-Jul-2024 15:00 | - | |
| mmlu:subject=us_foreign_policy,method=multiple_choice_joint,model=openai_gpt-4o-mini-2024-07-18/ | 23-Jul-2024 15:00 | - | |
| narrative_qa:model=mistralai_open-mistral-nemo-2407/ | 23-Jul-2024 15:00 | - | |
| natural_qa:mode=closedbook,model=mistralai_open-mistral-nemo-2407/ | 23-Jul-2024 15:00 | - | |
| natural_qa:mode=closedbook,model=microsoft_phi-3-medium-4k-instruct/ | 23-Jul-2024 15:00 | - | |
| natural_qa:mode=closedbook,model=microsoft_phi-3-small-8k-instruct/ | 23-Jul-2024 15:00 | - | |
| narrative_qa:model=openai_gpt-4o-mini-2024-07-18/ | 23-Jul-2024 15:00 | - | |
| narrative_qa:model=microsoft_phi-3-medium-4k-instruct/ | 23-Jul-2024 15:00 | - | |
| narrative_qa:model=microsoft_phi-3-small-8k-instruct/ | 23-Jul-2024 15:00 | - | |
| natural_qa:mode=closedbook,model=openai_gpt-4o-mini-2024-07-18/ | 23-Jul-2024 15:00 | - | |
| natural_qa:mode=openbook_longans,model=mistralai_open-mistral-nemo-2407/ | 23-Jul-2024 15:00 | - | |
| natural_qa:mode=openbook_longans,model=openai_gpt-4o-mini-2024-07-18/ | 23-Jul-2024 15:00 | - | |
| natural_qa:mode=openbook_longans,model=microsoft_phi-3-medium-4k-instruct/ | 23-Jul-2024 15:00 | - | |
| natural_qa:mode=openbook_longans,model=microsoft_phi-3-small-8k-instruct/ | 23-Jul-2024 15:00 | - | |
| wmt_14:language_pair=cs-en,model=microsoft_phi-3-small-8k-instruct/ | 23-Jul-2024 15:00 | - | |
| wmt_14:language_pair=cs-en,model=mistralai_open-mistral-nemo-2407/ | 23-Jul-2024 15:00 | - | |
| wmt_14:language_pair=cs-en,model=openai_gpt-4o-mini-2024-07-18/ | 23-Jul-2024 15:00 | - | |
| wmt_14:language_pair=cs-en,model=microsoft_phi-3-medium-4k-instruct/ | 23-Jul-2024 15:00 | - | |
| wmt_14:language_pair=de-en,model=microsoft_phi-3-medium-4k-instruct/ | 23-Jul-2024 15:00 | - | |
| wmt_14:language_pair=fr-en,model=mistralai_open-mistral-nemo-2407/ | 23-Jul-2024 15:00 | - | |
| wmt_14:language_pair=de-en,model=openai_gpt-4o-mini-2024-07-18/ | 23-Jul-2024 15:00 | - | |
| wmt_14:language_pair=de-en,model=mistralai_open-mistral-nemo-2407/ | 23-Jul-2024 15:00 | - | |
| wmt_14:language_pair=de-en,model=microsoft_phi-3-small-8k-instruct/ | 23-Jul-2024 15:00 | - | |
| wmt_14:language_pair=fr-en,model=openai_gpt-4o-mini-2024-07-18/ | 23-Jul-2024 15:00 | - | |
| wmt_14:language_pair=fr-en,model=microsoft_phi-3-medium-4k-instruct/ | 23-Jul-2024 15:00 | - | |
| wmt_14:language_pair=fr-en,model=microsoft_phi-3-small-8k-instruct/ | 23-Jul-2024 15:00 | - | |
| wmt_14:language_pair=hi-en,model=openai_gpt-4o-mini-2024-07-18/ | 23-Jul-2024 15:00 | - | |
| wmt_14:language_pair=hi-en,model=mistralai_open-mistral-nemo-2407/ | 23-Jul-2024 15:00 | - | |
| wmt_14:language_pair=hi-en,model=microsoft_phi-3-medium-4k-instruct/ | 23-Jul-2024 15:00 | - | |
| wmt_14:language_pair=ru-en,model=microsoft_phi-3-small-8k-instruct/ | 23-Jul-2024 15:00 | - | |
| wmt_14:language_pair=ru-en,model=mistralai_open-mistral-nemo-2407/ | 23-Jul-2024 15:00 | - | |
| wmt_14:language_pair=hi-en,model=microsoft_phi-3-small-8k-instruct/ | 23-Jul-2024 15:00 | - | |
| wmt_14:language_pair=ru-en,model=microsoft_phi-3-medium-4k-instruct/ | 23-Jul-2024 15:00 | - | |
| wmt_14:language_pair=ru-en,model=openai_gpt-4o-mini-2024-07-18/ | 23-Jul-2024 15:00 | - | |
| legalbench:subset=proa,model=meta_llama-3.1-8b-instruct-turbo/ | 24-Jul-2024 14:09 | - | |
| legalbench:subset=abercrombie,model=meta_llama-3.1-70b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| gsm:model=meta_llama-3.1-70b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| gsm:model=meta_llama-3.1-405b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| legalbench:subset=abercrombie,model=meta_llama-3.1-405b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| commonsense:dataset=openbookqa,method=multiple_choice_joint,model=meta_llama-3.1-70b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| commonsense:dataset=openbookqa,method=multiple_choice_joint,model=meta_llama-3.1-8b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| commonsense:dataset=openbookqa,method=multiple_choice_joint,model=meta_llama-3.1-405b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| gsm:model=meta_llama-3.1-8b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| legalbench:subset=abercrombie,model=meta_llama-3.1-8b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| legalbench:subset=function_of_decision_section,model=meta_llama-3.1-405b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| legalbench:subset=corporate_lobbying,model=meta_llama-3.1-405b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| legalbench:subset=corporate_lobbying,model=meta_llama-3.1-70b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| legalbench:subset=corporate_lobbying,model=meta_llama-3.1-8b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| legalbench:subset=function_of_decision_section,model=meta_llama-3.1-8b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| legalbench:subset=function_of_decision_section,model=meta_llama-3.1-70b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| legalbench:subset=international_citizenship_questions,model=meta_llama-3.1-405b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| legalbench:subset=international_citizenship_questions,model=meta_llama-3.1-70b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| legalbench:subset=international_citizenship_questions,model=meta_llama-3.1-8b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| legalbench:subset=proa,model=meta_llama-3.1-70b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| math:subject=algebra,level=1,use_official_examples=False,use_chain_of_thought=True,model=meta_llama-3.1-405b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| legalbench:subset=proa,model=meta_llama-3.1-405b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| math:subject=algebra,level=1,use_official_examples=False,use_chain_of_thought=True,model=meta_llama-3.1-8b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| math:subject=algebra,level=1,use_official_examples=False,use_chain_of_thought=True,model=meta_llama-3.1-70b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=meta_llama-3.1-405b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=meta_llama-3.1-8b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=meta_llama-3.1-70b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=meta_llama-3.1-405b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=meta_llama-3.1-70b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=meta_llama-3.1-8b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| math:subject=intermediate_algebra,level=1,use_official_examples=False,use_chain_of_thought=True,model=meta_llama-3.1-70b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| math:subject=number_theory,level=1,use_official_examples=False,use_chain_of_thought=True,model=meta_llama-3.1-405b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| math:subject=intermediate_algebra,level=1,use_official_examples=False,use_chain_of_thought=True,model=meta_llama-3.1-8b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| math:subject=intermediate_algebra,level=1,use_official_examples=False,use_chain_of_thought=True,model=meta_llama-3.1-405b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| math:subject=number_theory,level=1,use_official_examples=False,use_chain_of_thought=True,model=meta_llama-3.1-70b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| math:subject=number_theory,level=1,use_official_examples=False,use_chain_of_thought=True,model=meta_llama-3.1-8b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| math:subject=precalculus,level=1,use_official_examples=False,use_chain_of_thought=True,model=meta_llama-3.1-405b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| math:subject=prealgebra,level=1,use_official_examples=False,use_chain_of_thought=True,model=meta_llama-3.1-405b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| math:subject=prealgebra,level=1,use_official_examples=False,use_chain_of_thought=True,model=meta_llama-3.1-8b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| math:subject=prealgebra,level=1,use_official_examples=False,use_chain_of_thought=True,model=meta_llama-3.1-70b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| math:subject=precalculus,level=1,use_official_examples=False,use_chain_of_thought=True,model=meta_llama-3.1-70b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| math:subject=precalculus,level=1,use_official_examples=False,use_chain_of_thought=True,model=meta_llama-3.1-8b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| med_qa:model=meta_llama-3.1-405b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| med_qa:model=meta_llama-3.1-8b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| mmlu:subject=abstract_algebra,method=multiple_choice_joint,model=meta_llama-3.1-8b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| mmlu:subject=abstract_algebra,method=multiple_choice_joint,model=meta_llama-3.1-405b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| med_qa:model=meta_llama-3.1-70b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| mmlu:subject=abstract_algebra,method=multiple_choice_joint,model=meta_llama-3.1-70b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| mmlu:subject=college_chemistry,method=multiple_choice_joint,model=meta_llama-3.1-405b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| mmlu:subject=college_chemistry,method=multiple_choice_joint,model=meta_llama-3.1-70b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| mmlu:subject=college_chemistry,method=multiple_choice_joint,model=meta_llama-3.1-8b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| mmlu:subject=computer_security,method=multiple_choice_joint,model=meta_llama-3.1-8b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| mmlu:subject=computer_security,method=multiple_choice_joint,model=meta_llama-3.1-70b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| mmlu:subject=computer_security,method=multiple_choice_joint,model=meta_llama-3.1-405b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| mmlu:subject=econometrics,method=multiple_choice_joint,model=meta_llama-3.1-405b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| mmlu:subject=econometrics,method=multiple_choice_joint,model=meta_llama-3.1-70b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| mmlu:subject=econometrics,method=multiple_choice_joint,model=meta_llama-3.1-8b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| mmlu:subject=us_foreign_policy,method=multiple_choice_joint,model=meta_llama-3.1-405b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| mmlu:subject=us_foreign_policy,method=multiple_choice_joint,model=meta_llama-3.1-8b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| mmlu:subject=us_foreign_policy,method=multiple_choice_joint,model=meta_llama-3.1-70b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| narrative_qa:model=meta_llama-3.1-8b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| narrative_qa:model=meta_llama-3.1-70b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| narrative_qa:model=meta_llama-3.1-405b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| natural_qa:mode=closedbook,model=meta_llama-3.1-405b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| natural_qa:mode=closedbook,model=meta_llama-3.1-8b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| natural_qa:mode=closedbook,model=meta_llama-3.1-70b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| natural_qa:mode=openbook_longans,model=meta_llama-3.1-405b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| natural_qa:mode=openbook_longans,model=meta_llama-3.1-8b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| natural_qa:mode=openbook_longans,model=meta_llama-3.1-70b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| wmt_14:language_pair=cs-en,model=meta_llama-3.1-8b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| wmt_14:language_pair=cs-en,model=meta_llama-3.1-405b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| wmt_14:language_pair=cs-en,model=meta_llama-3.1-70b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| wmt_14:language_pair=de-en,model=meta_llama-3.1-405b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| wmt_14:language_pair=de-en,model=meta_llama-3.1-8b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| wmt_14:language_pair=de-en,model=meta_llama-3.1-70b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| wmt_14:language_pair=fr-en,model=meta_llama-3.1-405b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| wmt_14:language_pair=fr-en,model=meta_llama-3.1-8b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| wmt_14:language_pair=fr-en,model=meta_llama-3.1-70b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| wmt_14:language_pair=hi-en,model=meta_llama-3.1-70b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| wmt_14:language_pair=hi-en,model=meta_llama-3.1-405b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| wmt_14:language_pair=hi-en,model=meta_llama-3.1-8b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| wmt_14:language_pair=ru-en,model=meta_llama-3.1-405b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| wmt_14:language_pair=ru-en,model=meta_llama-3.1-8b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| wmt_14:language_pair=ru-en,model=meta_llama-3.1-70b-instruct-turbo/ | 24-Jul-2024 17:05 | - | |
| commonsense:dataset=openbookqa,method=multiple_choice_joint,model=google_gemma-2-27b/ | 25-Jul-2024 15:09 | - | |
| commonsense:dataset=openbookqa,method=multiple_choice_joint,model=google_gemma-2-9b/ | 25-Jul-2024 15:09 | - | |
| gsm:model=google_gemma-2-9b/ | 25-Jul-2024 15:09 | - | |
| legalbench:subset=abercrombie,model=google_gemma-2-9b/ | 25-Jul-2024 15:09 | - | |
| legalbench:subset=corporate_lobbying,model=google_gemma-2-9b/ | 25-Jul-2024 15:09 | - | |
| legalbench:subset=function_of_decision_section,model=google_gemma-2-9b/ | 25-Jul-2024 15:09 | - | |
| legalbench:subset=international_citizenship_questions,model=google_gemma-2-9b/ | 25-Jul-2024 15:09 | - | |
| legalbench:subset=proa,model=google_gemma-2-9b/ | 25-Jul-2024 15:09 | - | |
| math:subject=algebra,level=1,use_official_examples=False,use_chain_of_thought=True,model=google_gemma-2-9b/ | 25-Jul-2024 15:09 | - | |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=google_gemma-2-9b/ | 25-Jul-2024 15:09 | - | |
| math:subject=intermediate_algebra,level=1,use_official_examples=False,use_chain_of_thought=True,model=google_gemma-2-27b/ | 25-Jul-2024 15:09 | - | |
| math:subject=intermediate_algebra,level=1,use_official_examples=False,use_chain_of_thought=True,model=google_gemma-2-9b/ | 25-Jul-2024 15:09 | - | |
| math:subject=number_theory,level=1,use_official_examples=False,use_chain_of_thought=True,model=google_gemma-2-9b/ | 25-Jul-2024 15:09 | - | |
| math:subject=number_theory,level=1,use_official_examples=False,use_chain_of_thought=True,model=google_gemma-2-27b/ | 25-Jul-2024 15:09 | - | |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=google_gemma-2-9b/ | 25-Jul-2024 15:09 | - | |
| math:subject=prealgebra,level=1,use_official_examples=False,use_chain_of_thought=True,model=google_gemma-2-9b/ | 25-Jul-2024 15:09 | - | |
| math:subject=precalculus,level=1,use_official_examples=False,use_chain_of_thought=True,model=google_gemma-2-9b/ | 25-Jul-2024 15:09 | - | |
| mmlu:subject=abstract_algebra,method=multiple_choice_joint,model=google_gemma-2-9b/ | 25-Jul-2024 15:09 | - | |
| mmlu:subject=abstract_algebra,method=multiple_choice_joint,model=google_gemma-2-27b/ | 25-Jul-2024 15:09 | - | |
| med_qa:model=google_gemma-2-9b/ | 25-Jul-2024 15:09 | - | |
| mmlu:subject=college_chemistry,method=multiple_choice_joint,model=google_gemma-2-27b/ | 25-Jul-2024 15:09 | - | |
| mmlu:subject=college_chemistry,method=multiple_choice_joint,model=google_gemma-2-9b/ | 25-Jul-2024 15:09 | - | |
| mmlu:subject=computer_security,method=multiple_choice_joint,model=google_gemma-2-9b/ | 25-Jul-2024 15:09 | - | |
| mmlu:subject=computer_security,method=multiple_choice_joint,model=google_gemma-2-27b/ | 25-Jul-2024 15:09 | - | |
| mmlu:subject=econometrics,method=multiple_choice_joint,model=google_gemma-2-9b/ | 25-Jul-2024 15:09 | - | |
| mmlu:subject=econometrics,method=multiple_choice_joint,model=google_gemma-2-27b/ | 25-Jul-2024 15:09 | - | |
| mmlu:subject=us_foreign_policy,method=multiple_choice_joint,model=google_gemma-2-9b/ | 25-Jul-2024 15:09 | - | |
| mmlu:subject=us_foreign_policy,method=multiple_choice_joint,model=google_gemma-2-27b/ | 25-Jul-2024 15:09 | - | |
| natural_qa:mode=closedbook,model=google_gemma-2-9b/ | 25-Jul-2024 15:09 | - | |
| natural_qa:mode=closedbook,model=google_gemma-2-27b/ | 25-Jul-2024 15:09 | - | |
| narrative_qa:model=google_gemma-2-9b/ | 25-Jul-2024 15:09 | - | |
| narrative_qa:model=google_gemma-2-27b/ | 25-Jul-2024 15:09 | - | |
| natural_qa:mode=openbook_longans,model=google_gemma-2-27b/ | 25-Jul-2024 15:09 | - | |
| natural_qa:mode=openbook_longans,model=google_gemma-2-9b/ | 25-Jul-2024 15:09 | - | |
| wmt_14:language_pair=cs-en,model=google_gemma-2-9b/ | 25-Jul-2024 15:09 | - | |
| wmt_14:language_pair=de-en,model=google_gemma-2-9b/ | 25-Jul-2024 15:09 | - | |
| wmt_14:language_pair=fr-en,model=google_gemma-2-9b/ | 25-Jul-2024 15:09 | - | |
| wmt_14:language_pair=hi-en,model=google_gemma-2-9b/ | 25-Jul-2024 15:09 | - | |
| wmt_14:language_pair=ru-en,model=google_gemma-2-9b/ | 25-Jul-2024 15:09 | - | |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=google_gemma-2-27b/ | 25-Jul-2024 16:07 | - | |
| legalbench:subset=function_of_decision_section,model=ai21_jamba-instruct/ | 25-Jul-2024 16:15 | - | |
| gsm:model=ai21_jamba-instruct,stop=none/ | 25-Jul-2024 16:15 | - | |
| legalbench:subset=international_citizenship_questions,model=ai21_jamba-instruct/ | 25-Jul-2024 16:15 | - | |
| commonsense:dataset=openbookqa,method=multiple_choice_joint,model=ai21_jamba-instruct/ | 25-Jul-2024 16:15 | - | |
| legalbench:subset=abercrombie,model=ai21_jamba-instruct/ | 25-Jul-2024 16:15 | - | |
| legalbench:subset=corporate_lobbying,model=ai21_jamba-instruct/ | 25-Jul-2024 16:15 | - | |
| legalbench:subset=proa,model=ai21_jamba-instruct/ | 25-Jul-2024 16:15 | - | |
| math:subject=counting_and_probability,level=1,use_official_examples=False,use_chain_of_thought=True,model=ai21_jamba-instruct/ | 25-Jul-2024 16:15 | - | |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=ai21_jamba-instruct/ | 25-Jul-2024 16:15 | - | |
| math:subject=algebra,level=1,use_official_examples=False,use_chain_of_thought=True,model=ai21_jamba-instruct/ | 25-Jul-2024 16:15 | - | |
| math:subject=algebra,level=1,use_official_examples=False,use_chain_of_thought=True,model=google_gemma-2-27b/ | 25-Jul-2024 16:15 | - | |
| math:subject=geometry,level=1,use_official_examples=False,use_chain_of_thought=True,model=google_gemma-2-27b/ | 25-Jul-2024 16:15 | - | |
| math:subject=intermediate_algebra,level=1,use_official_examples=False,use_chain_of_thought=True,model=ai21_jamba-instruct/ | 25-Jul-2024 16:15 | - | |
| math:subject=number_theory,level=1,use_official_examples=False,use_chain_of_thought=True,model=ai21_jamba-instruct/ | 25-Jul-2024 16:15 | - | |
| math:subject=prealgebra,level=1,use_official_examples=False,use_chain_of_thought=True,model=ai21_jamba-instruct/ | 25-Jul-2024 16:15 | - | |
| math:subject=precalculus,level=1,use_official_examples=False,use_chain_of_thought=True,model=ai21_jamba-instruct/ | 25-Jul-2024 16:15 | - | |
| math:subject=prealgebra,level=1,use_official_examples=False,use_chain_of_thought=True,model=google_gemma-2-27b/ | 25-Jul-2024 16:15 | - | |
| med_qa:model=ai21_jamba-instruct/ | 25-Jul-2024 16:15 | - | |
| mmlu:subject=abstract_algebra,method=multiple_choice_joint,model=ai21_jamba-instruct/ | 25-Jul-2024 16:15 | - | |
| mmlu:subject=college_chemistry,method=multiple_choice_joint,model=ai21_jamba-instruct/ | 25-Jul-2024 16:15 | - | |
| mmlu:subject=computer_security,method=multiple_choice_joint,model=ai21_jamba-instruct/ | 25-Jul-2024 16:15 | - | |
| mmlu:subject=econometrics,method=multiple_choice_joint,model=ai21_jamba-instruct/ | 25-Jul-2024 16:15 | - | |
| mmlu:subject=us_foreign_policy,method=multiple_choice_joint,model=ai21_jamba-instruct/ | 25-Jul-2024 16:15 | - | |
| natural_qa:mode=closedbook,model=ai21_jamba-instruct/ | 25-Jul-2024 16:15 | - | |
| narrative_qa:model=ai21_jamba-instruct/ | 25-Jul-2024 16:15 | - | |
| wmt_14:language_pair=de-en,model=ai21_jamba-instruct/ | 25-Jul-2024 16:15 | - | |
| natural_qa:mode=openbook_longans,model=ai21_jamba-instruct/ | 25-Jul-2024 16:15 | - | |
| wmt_14:language_pair=cs-en,model=ai21_jamba-instruct/ | 25-Jul-2024 16:15 | - | |
| wmt_14:language_pair=fr-en,model=ai21_jamba-instruct/ | 25-Jul-2024 16:15 | - | |
| wmt_14:language_pair=hi-en,model=ai21_jamba-instruct/ | 25-Jul-2024 16:15 | - | |
| wmt_14:language_pair=ru-en,model=ai21_jamba-instruct/ | 25-Jul-2024 16:15 | - | |
|
|---|