![[ICO]](/icons/blank.gif) | Name | Last modified | Size | Description |
|---|
|
|---|
![[DIR]](/icons/back.gif) | Parent Directory | | - | |
![[DIR]](/icons/folder.gif) | eval_cache/ | 10-Jun-2024 23:18 | - | |
| live_qa:model=google_gemini-1.5-pro-preview-0409/ | 11-Jun-2024 12:25 | - | |
| live_qa:model=google_medlm-medium/ | 11-Jun-2024 12:25 | - | |
| live_qa:model=anthropic_claude-3-opus-20240229/ | 11-Jun-2024 12:25 | - | |
| live_qa:model=google_medlm-large,stop=none/ | 11-Jun-2024 12:25 | - | |
| live_qa:model=biomistral_biomistral-7b/ | 11-Jun-2024 12:25 | - | |
| live_qa:model=google_text-bison@002/ | 11-Jun-2024 12:25 | - | |
| live_qa:model=anthropic_claude-3-sonnet-20240229/ | 11-Jun-2024 12:25 | - | |
| live_qa:model=anthropic_claude-3-haiku-20240307/ | 11-Jun-2024 12:25 | - | |
| live_qa:model=google_text-unicorn@001/ | 11-Jun-2024 12:25 | - | |
| live_qa:model=mistralai_mixtral-8x22b/ | 11-Jun-2024 12:25 | - | |
| live_qa:model=meta_llama-3-70b/ | 11-Jun-2024 12:25 | - | |
| live_qa:model=mistralai_mistral-7b-instruct-v0.1/ | 11-Jun-2024 12:25 | - | |
| live_qa:model=openai_gpt-3.5-turbo-0125/ | 11-Jun-2024 12:25 | - | |
| live_qa:model=openai_gpt-4-turbo-2024-04-09/ | 11-Jun-2024 12:25 | - | |
| live_qa:model=openai_gpt-4o-2024-05-13/ | 11-Jun-2024 12:25 | - | |
| med_mcqa:model=google_text-bison@002,max_train_instances=0/ | 11-Jun-2024 12:25 | - | |
| med_mcqa:model=anthropic_claude-3-haiku-20240307,max_train_instances=0/ | 11-Jun-2024 12:25 | - | |
| med_mcqa:model=anthropic_claude-3-opus-20240229,max_train_instances=0/ | 11-Jun-2024 12:25 | - | |
| med_mcqa:model=google_medlm-medium,max_train_instances=0/ | 11-Jun-2024 12:25 | - | |
| med_mcqa:model=google_gemini-1.5-pro-preview-0409,max_train_instances=0/ | 11-Jun-2024 12:25 | - | |
| med_mcqa:model=anthropic_claude-3-sonnet-20240229,max_train_instances=0/ | 11-Jun-2024 12:25 | - | |
| med_mcqa:model=google_medlm-large,max_train_instances=0,stop=none/ | 11-Jun-2024 12:25 | - | |
| med_mcqa:model=biomistral_biomistral-7b,max_train_instances=0/ | 11-Jun-2024 12:25 | - | |
| med_mcqa:model=meta_llama-3-70b,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| med_mcqa:model=mistralai_mixtral-8x22b,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| med_mcqa:model=mistralai_mistral-7b-instruct-v0.1,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| med_mcqa:model=google_text-unicorn@001,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| med_mcqa:model=openai_gpt-3.5-turbo-0125,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| med_mcqa:model=openai_gpt-4-turbo-2024-04-09,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| med_qa:eval_split=test,model=anthropic_claude-3-haiku-20240307,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| med_mcqa:model=openai_gpt-4o-2024-05-13,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| med_qa:eval_split=test,model=anthropic_claude-3-opus-20240229,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| med_qa:eval_split=test,model=google_gemini-1.5-pro-preview-0409,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| med_qa:eval_split=test,model=anthropic_claude-3-sonnet-20240229,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| med_qa:eval_split=test,model=google_medlm-large,max_train_instances=0,stop=none/ | 11-Jun-2024 12:26 | - | |
| med_qa:eval_split=test,model=google_medlm-medium,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| med_qa:eval_split=test,model=biomistral_biomistral-7b,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| med_qa:eval_split=test,model=google_text-unicorn@001,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| med_qa:eval_split=test,model=google_text-bison@002,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| med_qa:eval_split=test,model=mistralai_mistral-7b-instruct-v0.1,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| med_qa:eval_split=test,model=meta_llama-3-70b,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| med_qa:eval_split=test,model=mistralai_mixtral-8x22b,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| med_qa:eval_split=test,model=openai_gpt-3.5-turbo-0125,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| med_qa:eval_split=test,model=openai_gpt-4-turbo-2024-04-09,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| med_qa:eval_split=test,model=openai_gpt-4o-2024-05-13,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| medication_qa:model=biomistral_biomistral-7b/ | 11-Jun-2024 12:26 | - | |
| medication_qa:model=anthropic_claude-3-haiku-20240307/ | 11-Jun-2024 12:26 | - | |
| medication_qa:model=google_medlm-large,stop=none/ | 11-Jun-2024 12:26 | - | |
| medication_qa:model=google_gemini-1.5-pro-preview-0409/ | 11-Jun-2024 12:26 | - | |
| medication_qa:model=anthropic_claude-3-opus-20240229/ | 11-Jun-2024 12:26 | - | |
| medication_qa:model=google_medlm-medium/ | 11-Jun-2024 12:26 | - | |
| medication_qa:model=google_text-unicorn@001/ | 11-Jun-2024 12:26 | - | |
| medication_qa:model=google_text-bison@002/ | 11-Jun-2024 12:26 | - | |
| medication_qa:model=anthropic_claude-3-sonnet-20240229/ | 11-Jun-2024 12:26 | - | |
| medication_qa:model=meta_llama-3-70b/ | 11-Jun-2024 12:26 | - | |
| medication_qa:model=mistralai_mixtral-8x22b/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=anatomy,method=multiple_choice_joint,eval_split=test,model=anthropic_claude-3-haiku-20240307,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=anatomy,method=multiple_choice_joint,eval_split=test,model=anthropic_claude-3-opus-20240229,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| medication_qa:model=openai_gpt-4o-2024-05-13/ | 11-Jun-2024 12:26 | - | |
| medication_qa:model=mistralai_mistral-7b-instruct-v0.1/ | 11-Jun-2024 12:26 | - | |
| medication_qa:model=openai_gpt-3.5-turbo-0125/ | 11-Jun-2024 12:26 | - | |
| medication_qa:model=openai_gpt-4-turbo-2024-04-09/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=anatomy,method=multiple_choice_joint,eval_split=test,model=anthropic_claude-3-sonnet-20240229,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=anatomy,method=multiple_choice_joint,eval_split=test,model=google_gemini-1.5-pro-preview-0409,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=anatomy,method=multiple_choice_joint,eval_split=test,model=biomistral_biomistral-7b,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=anatomy,method=multiple_choice_joint,eval_split=test,model=google_medlm-large,max_train_instances=0,stop=none/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=anatomy,method=multiple_choice_joint,eval_split=test,model=google_text-unicorn@001,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=anatomy,method=multiple_choice_joint,eval_split=test,model=google_text-bison@002,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=anatomy,method=multiple_choice_joint,eval_split=test,model=mistralai_mistral-7b-instruct-v0.1,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=anatomy,method=multiple_choice_joint,eval_split=test,model=google_medlm-medium,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=anatomy,method=multiple_choice_joint,eval_split=test,model=mistralai_mixtral-8x22b,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=anatomy,method=multiple_choice_joint,eval_split=test,model=openai_gpt-3.5-turbo-0125,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=anatomy,method=multiple_choice_joint,eval_split=test,model=openai_gpt-4-turbo-2024-04-09,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=anatomy,method=multiple_choice_joint,eval_split=test,model=meta_llama-3-70b,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=anatomy,method=multiple_choice_joint,eval_split=test,model=openai_gpt-4o-2024-05-13,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=clinical_knowledge,method=multiple_choice_joint,eval_split=test,model=anthropic_claude-3-sonnet-20240229,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=clinical_knowledge,method=multiple_choice_joint,eval_split=test,model=google_gemini-1.5-pro-preview-0409,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=clinical_knowledge,method=multiple_choice_joint,eval_split=test,model=anthropic_claude-3-haiku-20240307,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=clinical_knowledge,method=multiple_choice_joint,eval_split=test,model=biomistral_biomistral-7b,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=clinical_knowledge,method=multiple_choice_joint,eval_split=test,model=anthropic_claude-3-opus-20240229,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=clinical_knowledge,method=multiple_choice_joint,eval_split=test,model=google_medlm-large,max_train_instances=0,stop=none/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=clinical_knowledge,method=multiple_choice_joint,eval_split=test,model=google_medlm-medium,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=clinical_knowledge,method=multiple_choice_joint,eval_split=test,model=google_text-bison@002,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=clinical_knowledge,method=multiple_choice_joint,eval_split=test,model=mistralai_mixtral-8x22b,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=clinical_knowledge,method=multiple_choice_joint,eval_split=test,model=google_text-unicorn@001,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=clinical_knowledge,method=multiple_choice_joint,eval_split=test,model=mistralai_mistral-7b-instruct-v0.1,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=college_biology,method=multiple_choice_joint,eval_split=test,model=anthropic_claude-3-haiku-20240307,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=clinical_knowledge,method=multiple_choice_joint,eval_split=test,model=meta_llama-3-70b,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=clinical_knowledge,method=multiple_choice_joint,eval_split=test,model=openai_gpt-4o-2024-05-13,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=clinical_knowledge,method=multiple_choice_joint,eval_split=test,model=openai_gpt-4-turbo-2024-04-09,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=clinical_knowledge,method=multiple_choice_joint,eval_split=test,model=openai_gpt-3.5-turbo-0125,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=college_biology,method=multiple_choice_joint,eval_split=test,model=anthropic_claude-3-opus-20240229,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=college_biology,method=multiple_choice_joint,eval_split=test,model=biomistral_biomistral-7b,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=college_biology,method=multiple_choice_joint,eval_split=test,model=google_medlm-large,max_train_instances=0,stop=none/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=college_biology,method=multiple_choice_joint,eval_split=test,model=anthropic_claude-3-sonnet-20240229,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=college_biology,method=multiple_choice_joint,eval_split=test,model=google_gemini-1.5-pro-preview-0409,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=college_biology,method=multiple_choice_joint,eval_split=test,model=google_medlm-medium,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=college_biology,method=multiple_choice_joint,eval_split=test,model=google_text-unicorn@001,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=college_biology,method=multiple_choice_joint,eval_split=test,model=google_text-bison@002,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=college_biology,method=multiple_choice_joint,eval_split=test,model=mistralai_mistral-7b-instruct-v0.1,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=college_biology,method=multiple_choice_joint,eval_split=test,model=meta_llama-3-70b,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=college_biology,method=multiple_choice_joint,eval_split=test,model=mistralai_mixtral-8x22b,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=college_biology,method=multiple_choice_joint,eval_split=test,model=openai_gpt-4-turbo-2024-04-09,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=college_biology,method=multiple_choice_joint,eval_split=test,model=openai_gpt-3.5-turbo-0125,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=college_biology,method=multiple_choice_joint,eval_split=test,model=openai_gpt-4o-2024-05-13,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=college_medicine,method=multiple_choice_joint,eval_split=test,model=anthropic_claude-3-haiku-20240307,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=college_medicine,method=multiple_choice_joint,eval_split=test,model=anthropic_claude-3-opus-20240229,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=college_medicine,method=multiple_choice_joint,eval_split=test,model=google_gemini-1.5-pro-preview-0409,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=college_medicine,method=multiple_choice_joint,eval_split=test,model=anthropic_claude-3-sonnet-20240229,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=college_medicine,method=multiple_choice_joint,eval_split=test,model=biomistral_biomistral-7b,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=college_medicine,method=multiple_choice_joint,eval_split=test,model=google_medlm-large,max_train_instances=0,stop=none/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=college_medicine,method=multiple_choice_joint,eval_split=test,model=google_medlm-medium,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=college_medicine,method=multiple_choice_joint,eval_split=test,model=google_text-bison@002,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=college_medicine,method=multiple_choice_joint,eval_split=test,model=meta_llama-3-70b,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=college_medicine,method=multiple_choice_joint,eval_split=test,model=google_text-unicorn@001,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=college_medicine,method=multiple_choice_joint,eval_split=test,model=openai_gpt-4-turbo-2024-04-09,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=college_medicine,method=multiple_choice_joint,eval_split=test,model=openai_gpt-3.5-turbo-0125,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=college_medicine,method=multiple_choice_joint,eval_split=test,model=mistralai_mixtral-8x22b,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=college_medicine,method=multiple_choice_joint,eval_split=test,model=mistralai_mistral-7b-instruct-v0.1,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=medical_genetics,method=multiple_choice_joint,eval_split=test,model=anthropic_claude-3-haiku-20240307,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=college_medicine,method=multiple_choice_joint,eval_split=test,model=openai_gpt-4o-2024-05-13,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=medical_genetics,method=multiple_choice_joint,eval_split=test,model=anthropic_claude-3-opus-20240229,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=medical_genetics,method=multiple_choice_joint,eval_split=test,model=anthropic_claude-3-sonnet-20240229,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=medical_genetics,method=multiple_choice_joint,eval_split=test,model=biomistral_biomistral-7b,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=medical_genetics,method=multiple_choice_joint,eval_split=test,model=google_gemini-1.5-pro-preview-0409,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=medical_genetics,method=multiple_choice_joint,eval_split=test,model=google_medlm-large,max_train_instances=0,stop=none/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=medical_genetics,method=multiple_choice_joint,eval_split=test,model=google_medlm-medium,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=medical_genetics,method=multiple_choice_joint,eval_split=test,model=google_text-bison@002,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=medical_genetics,method=multiple_choice_joint,eval_split=test,model=mistralai_mistral-7b-instruct-v0.1,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=medical_genetics,method=multiple_choice_joint,eval_split=test,model=google_text-unicorn@001,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=medical_genetics,method=multiple_choice_joint,eval_split=test,model=meta_llama-3-70b,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=medical_genetics,method=multiple_choice_joint,eval_split=test,model=mistralai_mixtral-8x22b,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=medical_genetics,method=multiple_choice_joint,eval_split=test,model=openai_gpt-3.5-turbo-0125,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=medical_genetics,method=multiple_choice_joint,eval_split=test,model=openai_gpt-4-turbo-2024-04-09,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=medical_genetics,method=multiple_choice_joint,eval_split=test,model=openai_gpt-4o-2024-05-13,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=professional_medicine,method=multiple_choice_joint,eval_split=test,model=anthropic_claude-3-opus-20240229,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=professional_medicine,method=multiple_choice_joint,eval_split=test,model=anthropic_claude-3-sonnet-20240229,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=professional_medicine,method=multiple_choice_joint,eval_split=test,model=anthropic_claude-3-haiku-20240307,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=professional_medicine,method=multiple_choice_joint,eval_split=test,model=biomistral_biomistral-7b,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=professional_medicine,method=multiple_choice_joint,eval_split=test,model=google_medlm-large,max_train_instances=0,stop=none/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=professional_medicine,method=multiple_choice_joint,eval_split=test,model=google_medlm-medium,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=professional_medicine,method=multiple_choice_joint,eval_split=test,model=google_text-bison@002,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=professional_medicine,method=multiple_choice_joint,eval_split=test,model=google_gemini-1.5-pro-preview-0409,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=professional_medicine,method=multiple_choice_joint,eval_split=test,model=meta_llama-3-70b,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=professional_medicine,method=multiple_choice_joint,eval_split=test,model=google_text-unicorn@001,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=professional_medicine,method=multiple_choice_joint,eval_split=test,model=mistralai_mistral-7b-instruct-v0.1,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=professional_medicine,method=multiple_choice_joint,eval_split=test,model=openai_gpt-3.5-turbo-0125,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=professional_medicine,method=multiple_choice_joint,eval_split=test,model=mistralai_mixtral-8x22b,max_train_instances=0/ | 11-Jun-2024 12:26 | - | |
| mmlu:subject=professional_medicine,method=multiple_choice_joint,eval_split=test,model=openai_gpt-4-turbo-2024-04-09,max_train_instances=0/ | 11-Jun-2024 12:27 | - | |
| mmlu:subject=professional_medicine,method=multiple_choice_joint,eval_split=test,model=openai_gpt-4o-2024-05-13,max_train_instances=0/ | 11-Jun-2024 12:27 | - | |
| pubmed_qa:eval_split=test,model=biomistral_biomistral-7b,max_train_instances=0/ | 11-Jun-2024 12:27 | - | |
| pubmed_qa:eval_split=test,model=anthropic_claude-3-sonnet-20240229,max_train_instances=0/ | 11-Jun-2024 12:27 | - | |
| pubmed_qa:eval_split=test,model=anthropic_claude-3-haiku-20240307,max_train_instances=0/ | 11-Jun-2024 12:27 | - | |
| pubmed_qa:eval_split=test,model=google_gemini-1.5-pro-preview-0409,max_train_instances=0/ | 11-Jun-2024 12:27 | - | |
| pubmed_qa:eval_split=test,model=google_medlm-large,max_train_instances=0,stop=none/ | 11-Jun-2024 12:27 | - | |
| pubmed_qa:eval_split=test,model=anthropic_claude-3-opus-20240229,max_train_instances=0/ | 11-Jun-2024 12:27 | - | |
| pubmed_qa:eval_split=test,model=google_medlm-medium,max_train_instances=0/ | 11-Jun-2024 12:27 | - | |
| pubmed_qa:eval_split=test,model=google_text-bison@002,max_train_instances=0/ | 11-Jun-2024 12:27 | - | |
| pubmed_qa:eval_split=test,model=google_text-unicorn@001,max_train_instances=0/ | 11-Jun-2024 12:27 | - | |
| pubmed_qa:eval_split=test,model=meta_llama-3-70b,max_train_instances=0/ | 11-Jun-2024 12:27 | - | |
| pubmed_qa:eval_split=test,model=mistralai_mistral-7b-instruct-v0.1,max_train_instances=0/ | 11-Jun-2024 12:27 | - | |
| pubmed_qa:eval_split=test,model=openai_gpt-3.5-turbo-0125,max_train_instances=0/ | 11-Jun-2024 12:27 | - | |
| pubmed_qa:eval_split=test,model=mistralai_mixtral-8x22b,max_train_instances=0/ | 11-Jun-2024 12:27 | - | |
| pubmed_qa:eval_split=test,model=openai_gpt-4-turbo-2024-04-09,max_train_instances=0/ | 11-Jun-2024 12:27 | - | |
| pubmed_qa:eval_split=test,model=openai_gpt-4o-2024-05-13,max_train_instances=0/ | 11-Jun-2024 12:27 | - | |
| live_qa:model=epfl-llm_meditron-7b/ | 11-Jun-2024 13:00 | - | |
| live_qa:model=meta_llama-2-7b/ | 11-Jun-2024 13:00 | - | |
| med_mcqa:model=epfl-llm_meditron-7b,max_train_instances=0/ | 11-Jun-2024 13:00 | - | |
| med_qa:eval_split=test,model=epfl-llm_meditron-7b,max_train_instances=0/ | 11-Jun-2024 13:00 | - | |
| med_mcqa:model=meta_llama-2-7b,max_train_instances=0/ | 11-Jun-2024 13:00 | - | |
| medication_qa:model=epfl-llm_meditron-7b/ | 11-Jun-2024 13:00 | - | |
| med_qa:eval_split=test,model=meta_llama-2-7b,max_train_instances=0/ | 11-Jun-2024 13:00 | - | |
| mmlu:subject=anatomy,method=multiple_choice_joint,eval_split=test,model=epfl-llm_meditron-7b,max_train_instances=0/ | 11-Jun-2024 13:00 | - | |
| medication_qa:model=meta_llama-2-7b/ | 11-Jun-2024 13:00 | - | |
| mmlu:subject=anatomy,method=multiple_choice_joint,eval_split=test,model=meta_llama-2-7b,max_train_instances=0/ | 11-Jun-2024 13:00 | - | |
| mmlu:subject=clinical_knowledge,method=multiple_choice_joint,eval_split=test,model=meta_llama-2-7b,max_train_instances=0/ | 11-Jun-2024 13:00 | - | |
| mmlu:subject=clinical_knowledge,method=multiple_choice_joint,eval_split=test,model=epfl-llm_meditron-7b,max_train_instances=0/ | 11-Jun-2024 13:00 | - | |
| mmlu:subject=college_biology,method=multiple_choice_joint,eval_split=test,model=epfl-llm_meditron-7b,max_train_instances=0/ | 11-Jun-2024 13:00 | - | |
| mmlu:subject=college_biology,method=multiple_choice_joint,eval_split=test,model=meta_llama-2-7b,max_train_instances=0/ | 11-Jun-2024 13:00 | - | |
| mmlu:subject=college_medicine,method=multiple_choice_joint,eval_split=test,model=epfl-llm_meditron-7b,max_train_instances=0/ | 11-Jun-2024 13:00 | - | |
| mmlu:subject=college_medicine,method=multiple_choice_joint,eval_split=test,model=meta_llama-2-7b,max_train_instances=0/ | 11-Jun-2024 13:00 | - | |
| mmlu:subject=medical_genetics,method=multiple_choice_joint,eval_split=test,model=epfl-llm_meditron-7b,max_train_instances=0/ | 11-Jun-2024 13:00 | - | |
| mmlu:subject=medical_genetics,method=multiple_choice_joint,eval_split=test,model=meta_llama-2-7b,max_train_instances=0/ | 11-Jun-2024 13:00 | - | |
| mmlu:subject=professional_medicine,method=multiple_choice_joint,eval_split=test,model=epfl-llm_meditron-7b,max_train_instances=0/ | 11-Jun-2024 13:00 | - | |
| mmlu:subject=professional_medicine,method=multiple_choice_joint,eval_split=test,model=meta_llama-2-7b,max_train_instances=0/ | 11-Jun-2024 13:00 | - | |
| pubmed_qa:eval_split=test,model=meta_llama-2-7b,max_train_instances=0/ | 11-Jun-2024 13:00 | - | |
| pubmed_qa:eval_split=test,model=epfl-llm_meditron-7b,max_train_instances=0/ | 11-Jun-2024 13:00 | - | |
|
|---|