Safety
MMLU Business Ethics
MMLU business_ethics per-(model, question) accuracy (acc in {0,1}) over an applied-ethics MCQ subject, from the Open LLM Leaderboard v1 details datasets. Model panel capped to 150.
100items
150subjects
MITlicense
knowledgedomain
reasoningdomain
textmodality
item-level responses released
Saturation status: Unknown
Response matrix
Fit to width. Hover for subject & item; click a cell for details.
Correct (1)Incorrect (0)Unobserved
Scale: 1 = correct · 0 = incorrect
Subjects
- 1quantumaikr__llama-2-70b-fb16-guanaco-1k0.76
- 2liuxiang886__llama2-70B-qlora-gpt40.76
- 3upstage__Llama-2-70b-instruct0.76
- 4jordiclive__Llama-2-70b-oasst-1-2000.76
- 5augtoma__qCammel-70-x0.75
- 6deepnight-research__llama-2-70B-inst0.74
- 7upstage__Llama-2-70b-instruct-v20.74
- 8jarradh__llama2_70b_chat_uncensored0.73
- 9MayaPH__GodziLLa2-70B0.71
- 10upstage__llama-65b-instruct0.68
- 11WizardLM__WizardLM-70B-V1.00.68
- 12OpenBuddy__openbuddy-llama-65b-v8-bf160.65
- 13lilloukas__Platypus-30B0.64
- 14lilloukas__GPlatty-30B0.64
- 15camel-ai__CAMEL-33B-Combined-Data0.63
- 16upstage__llama-30b-instruct-20480.62
- 17quantumaikr__QuantumLM-70B-hf0.62
- 18MayaPH__GodziLLa-30B0.61
- 19upstage__llama-30b-instruct0.61
- 20NousResearch__Nous-Hermes-Llama2-13b0.6
- 21OpenBuddy__openbuddy-llama2-13b-v8.1-fp160.6
- 22augtoma__qCammel-130.57
- 23CalderaAI__30B-Lazarus0.57
- 24HiTZ__alpaca-lora-65b-en-pt-es-ca0.57
- 25mosaicml__mpt-30b-chat0.57
- 26shareAI__llama2-13b-Chinese-chat0.57
- 27NousResearch__Nous-Hermes-llama-2-7b0.57
- 28OpenBuddyEA__openbuddy-llama-30b-v7.1-bf160.56
- 29OptimalScale__robin-65b-v2-delta0.56
- 30Aeala__GPT4-x-AlpacaDente-30b0.56
- 31NousResearch__Redmond-Puffin-13B0.56
- 32garage-bAInd__Camel-Platypus2-13B0.55
- 33WizardLM__WizardLM-13B-V1.20.55
- 34Lajonbot__Llama-2-13b-hf-instruct-pl-lora_unload0.55
- 35camel-ai__CAMEL-13B-Combined-Data0.54
- 36kevinpro__Vicuna-13B-CoT0.54