Build latest book artifacts / build (push) Canceled after 0s
dependency resolution / resolve (3.11) (push) Canceled after 0s
dependency resolution / resolve (3.13) (push) Canceled after 0s
deploy-pages / build (push) Canceled after 0s
deploy-pages / deploy (push) Canceled after 0s
i18n consistency check / check (push) Canceled after 0s
provider adoption tests / test (chapter2/context-compression) (push) Canceled after 0s
provider adoption tests / test (chapter2/prompt-injection) (push) Canceled after 0s
provider adoption tests / test (chapter2/system-hint) (push) Canceled after 0s
provider adoption tests / test (chapter3/log-sanitization) (push) Canceled after 0s
web-search-agent tests / test (push) Canceled after 0s
web-search-agent tests / agentbook (push) Canceled after 0s
909 lines
36 KiB
JSON
909 lines
36 KiB
JSON
{
|
|
"empirical": {
|
|
"athene-70b-0725": {
|
|
"athene-70b-0725": 0.5,
|
|
"bard-jan-24-gemini-pro": NaN,
|
|
"chatgpt-4o-latest": 0.41589648798521256,
|
|
"claude-1": NaN,
|
|
"claude-2.0": NaN,
|
|
"claude-3-5-sonnet-20240620": 0.49077181208053694,
|
|
"claude-3-opus-20240229": 0.5027472527472527,
|
|
"gemini-1.5-pro-api-0409-preview": NaN,
|
|
"gemini-1.5-pro-exp-0801": 0.43097014925373134,
|
|
"gemini-advanced-0514": 0.48249027237354086,
|
|
"gemini-pro-dev-api": NaN,
|
|
"glm-4-0520": NaN,
|
|
"gpt-3.5-turbo-0314": NaN,
|
|
"gpt-4o-2024-05-13": 0.4431239388794567,
|
|
"gpt-4o-2024-08-06": 0.505249343832021,
|
|
"gpt-4o-mini-2024-07-18": 0.4753787878787879,
|
|
"llama-2-70b-chat": NaN,
|
|
"llama-3.1-70b-instruct": 0.5317460317460317,
|
|
"nemotron-4-340b-instruct": NaN,
|
|
"yi-large-preview": 0.5294117647058824
|
|
},
|
|
"bard-jan-24-gemini-pro": {
|
|
"athene-70b-0725": NaN,
|
|
"bard-jan-24-gemini-pro": 0.5,
|
|
"chatgpt-4o-latest": NaN,
|
|
"claude-1": 0.572289156626506,
|
|
"claude-2.0": 0.6696428571428571,
|
|
"claude-3-5-sonnet-20240620": NaN,
|
|
"claude-3-opus-20240229": 0.3,
|
|
"gemini-1.5-pro-api-0409-preview": NaN,
|
|
"gemini-1.5-pro-exp-0801": NaN,
|
|
"gemini-advanced-0514": NaN,
|
|
"gemini-pro-dev-api": 0.6332794830371568,
|
|
"glm-4-0520": NaN,
|
|
"gpt-3.5-turbo-0314": NaN,
|
|
"gpt-4o-2024-05-13": NaN,
|
|
"gpt-4o-2024-08-06": NaN,
|
|
"gpt-4o-mini-2024-07-18": NaN,
|
|
"llama-2-70b-chat": 0.6492537313432836,
|
|
"llama-3.1-70b-instruct": NaN,
|
|
"nemotron-4-340b-instruct": NaN,
|
|
"yi-large-preview": NaN
|
|
},
|
|
"chatgpt-4o-latest": {
|
|
"athene-70b-0725": 0.5841035120147874,
|
|
"bard-jan-24-gemini-pro": NaN,
|
|
"chatgpt-4o-latest": 0.5,
|
|
"claude-1": NaN,
|
|
"claude-2.0": NaN,
|
|
"claude-3-5-sonnet-20240620": 0.5534351145038168,
|
|
"claude-3-opus-20240229": 0.5915750915750916,
|
|
"gemini-1.5-pro-api-0409-preview": NaN,
|
|
"gemini-1.5-pro-exp-0801": 0.5329736211031175,
|
|
"gemini-advanced-0514": NaN,
|
|
"gemini-pro-dev-api": NaN,
|
|
"glm-4-0520": NaN,
|
|
"gpt-3.5-turbo-0314": NaN,
|
|
"gpt-4o-2024-05-13": 0.5442092154420921,
|
|
"gpt-4o-2024-08-06": 0.5164835164835165,
|
|
"gpt-4o-mini-2024-07-18": 0.6010733452593918,
|
|
"llama-2-70b-chat": NaN,
|
|
"llama-3.1-70b-instruct": 0.5793838862559242,
|
|
"nemotron-4-340b-instruct": NaN,
|
|
"yi-large-preview": NaN
|
|
},
|
|
"claude-1": {
|
|
"athene-70b-0725": NaN,
|
|
"bard-jan-24-gemini-pro": 0.42771084337349397,
|
|
"chatgpt-4o-latest": NaN,
|
|
"claude-1": 0.5,
|
|
"claude-2.0": 0.5460750853242321,
|
|
"claude-3-5-sonnet-20240620": NaN,
|
|
"claude-3-opus-20240229": 0.34452296819787986,
|
|
"gemini-1.5-pro-api-0409-preview": NaN,
|
|
"gemini-1.5-pro-exp-0801": NaN,
|
|
"gemini-advanced-0514": NaN,
|
|
"gemini-pro-dev-api": 0.5342465753424658,
|
|
"glm-4-0520": NaN,
|
|
"gpt-3.5-turbo-0314": 0.5548780487804879,
|
|
"gpt-4o-2024-05-13": NaN,
|
|
"gpt-4o-2024-08-06": NaN,
|
|
"gpt-4o-mini-2024-07-18": NaN,
|
|
"llama-2-70b-chat": 0.604,
|
|
"llama-3.1-70b-instruct": NaN,
|
|
"nemotron-4-340b-instruct": NaN,
|
|
"yi-large-preview": NaN
|
|
},
|
|
"claude-2.0": {
|
|
"athene-70b-0725": NaN,
|
|
"bard-jan-24-gemini-pro": 0.33035714285714285,
|
|
"chatgpt-4o-latest": NaN,
|
|
"claude-1": 0.4539249146757679,
|
|
"claude-2.0": 0.5,
|
|
"claude-3-5-sonnet-20240620": NaN,
|
|
"claude-3-opus-20240229": NaN,
|
|
"gemini-1.5-pro-api-0409-preview": NaN,
|
|
"gemini-1.5-pro-exp-0801": NaN,
|
|
"gemini-advanced-0514": NaN,
|
|
"gemini-pro-dev-api": 0.5569620253164557,
|
|
"glm-4-0520": NaN,
|
|
"gpt-3.5-turbo-0314": NaN,
|
|
"gpt-4o-2024-05-13": NaN,
|
|
"gpt-4o-2024-08-06": NaN,
|
|
"gpt-4o-mini-2024-07-18": NaN,
|
|
"llama-2-70b-chat": 0.5866834170854272,
|
|
"llama-3.1-70b-instruct": NaN,
|
|
"nemotron-4-340b-instruct": NaN,
|
|
"yi-large-preview": NaN
|
|
},
|
|
"claude-3-5-sonnet-20240620": {
|
|
"athene-70b-0725": 0.5092281879194631,
|
|
"bard-jan-24-gemini-pro": NaN,
|
|
"chatgpt-4o-latest": 0.44656488549618323,
|
|
"claude-1": NaN,
|
|
"claude-2.0": NaN,
|
|
"claude-3-5-sonnet-20240620": 0.5,
|
|
"claude-3-opus-20240229": 0.5447761194029851,
|
|
"gemini-1.5-pro-api-0409-preview": NaN,
|
|
"gemini-1.5-pro-exp-0801": 0.4537037037037037,
|
|
"gemini-advanced-0514": 0.49312714776632305,
|
|
"gemini-pro-dev-api": NaN,
|
|
"glm-4-0520": 0.5800756620428752,
|
|
"gpt-3.5-turbo-0314": NaN,
|
|
"gpt-4o-2024-05-13": 0.47875730217737655,
|
|
"gpt-4o-2024-08-06": 0.5189873417721519,
|
|
"gpt-4o-mini-2024-07-18": 0.47484909456740443,
|
|
"llama-2-70b-chat": NaN,
|
|
"llama-3.1-70b-instruct": 0.538961038961039,
|
|
"nemotron-4-340b-instruct": 0.589835728952772,
|
|
"yi-large-preview": 0.5205761316872428
|
|
},
|
|
"claude-3-opus-20240229": {
|
|
"athene-70b-0725": 0.49725274725274726,
|
|
"bard-jan-24-gemini-pro": 0.7,
|
|
"chatgpt-4o-latest": 0.4084249084249084,
|
|
"claude-1": 0.6554770318021201,
|
|
"claude-2.0": NaN,
|
|
"claude-3-5-sonnet-20240620": 0.4552238805970149,
|
|
"claude-3-opus-20240229": 0.5,
|
|
"gemini-1.5-pro-api-0409-preview": 0.4815616343490305,
|
|
"gemini-1.5-pro-exp-0801": 0.4305157593123209,
|
|
"gemini-advanced-0514": 0.46121231155778897,
|
|
"gemini-pro-dev-api": 0.6489533011272142,
|
|
"glm-4-0520": 0.5424311926605505,
|
|
"gpt-3.5-turbo-0314": NaN,
|
|
"gpt-4o-2024-05-13": 0.4481694338016177,
|
|
"gpt-4o-2024-08-06": 0.4369627507163324,
|
|
"gpt-4o-mini-2024-07-18": 0.4437386569872958,
|
|
"llama-2-70b-chat": 0.6890951276102089,
|
|
"llama-3.1-70b-instruct": 0.4813519813519814,
|
|
"nemotron-4-340b-instruct": 0.5431309904153354,
|
|
"yi-large-preview": 0.5238190552441954
|
|
},
|
|
"gemini-1.5-pro-api-0409-preview": {
|
|
"athene-70b-0725": NaN,
|
|
"bard-jan-24-gemini-pro": NaN,
|
|
"chatgpt-4o-latest": NaN,
|
|
"claude-1": NaN,
|
|
"claude-2.0": NaN,
|
|
"claude-3-5-sonnet-20240620": NaN,
|
|
"claude-3-opus-20240229": 0.5184383656509696,
|
|
"gemini-1.5-pro-api-0409-preview": 0.5,
|
|
"gemini-1.5-pro-exp-0801": NaN,
|
|
"gemini-advanced-0514": NaN,
|
|
"gemini-pro-dev-api": NaN,
|
|
"glm-4-0520": NaN,
|
|
"gpt-3.5-turbo-0314": NaN,
|
|
"gpt-4o-2024-05-13": NaN,
|
|
"gpt-4o-2024-08-06": NaN,
|
|
"gpt-4o-mini-2024-07-18": NaN,
|
|
"llama-2-70b-chat": 0.6875,
|
|
"llama-3.1-70b-instruct": NaN,
|
|
"nemotron-4-340b-instruct": NaN,
|
|
"yi-large-preview": NaN
|
|
},
|
|
"gemini-1.5-pro-exp-0801": {
|
|
"athene-70b-0725": 0.5690298507462687,
|
|
"bard-jan-24-gemini-pro": NaN,
|
|
"chatgpt-4o-latest": 0.4670263788968825,
|
|
"claude-1": NaN,
|
|
"claude-2.0": NaN,
|
|
"claude-3-5-sonnet-20240620": 0.5462962962962963,
|
|
"claude-3-opus-20240229": 0.5694842406876791,
|
|
"gemini-1.5-pro-api-0409-preview": NaN,
|
|
"gemini-1.5-pro-exp-0801": 0.5,
|
|
"gemini-advanced-0514": 0.5263157894736842,
|
|
"gemini-pro-dev-api": NaN,
|
|
"glm-4-0520": NaN,
|
|
"gpt-3.5-turbo-0314": NaN,
|
|
"gpt-4o-2024-05-13": 0.5229445506692161,
|
|
"gpt-4o-2024-08-06": 0.5241071428571429,
|
|
"gpt-4o-mini-2024-07-18": 0.529559748427673,
|
|
"llama-2-70b-chat": NaN,
|
|
"llama-3.1-70b-instruct": 0.5773092369477911,
|
|
"nemotron-4-340b-instruct": NaN,
|
|
"yi-large-preview": 0.5862068965517241
|
|
},
|
|
"gemini-advanced-0514": {
|
|
"athene-70b-0725": 0.5175097276264592,
|
|
"bard-jan-24-gemini-pro": NaN,
|
|
"chatgpt-4o-latest": NaN,
|
|
"claude-1": NaN,
|
|
"claude-2.0": NaN,
|
|
"claude-3-5-sonnet-20240620": 0.506872852233677,
|
|
"claude-3-opus-20240229": 0.538787688442211,
|
|
"gemini-1.5-pro-api-0409-preview": NaN,
|
|
"gemini-1.5-pro-exp-0801": 0.47368421052631576,
|
|
"gemini-advanced-0514": 0.5,
|
|
"gemini-pro-dev-api": NaN,
|
|
"glm-4-0520": 0.5773381294964028,
|
|
"gpt-3.5-turbo-0314": NaN,
|
|
"gpt-4o-2024-05-13": 0.4901780233271946,
|
|
"gpt-4o-2024-08-06": NaN,
|
|
"gpt-4o-mini-2024-07-18": 0.4604072398190045,
|
|
"llama-2-70b-chat": 0.6145833333333334,
|
|
"llama-3.1-70b-instruct": 0.5423076923076923,
|
|
"nemotron-4-340b-instruct": 0.5807407407407408,
|
|
"yi-large-preview": 0.5602636534839924
|
|
},
|
|
"gemini-pro-dev-api": {
|
|
"athene-70b-0725": NaN,
|
|
"bard-jan-24-gemini-pro": 0.3667205169628433,
|
|
"chatgpt-4o-latest": NaN,
|
|
"claude-1": 0.4657534246575342,
|
|
"claude-2.0": 0.4430379746835443,
|
|
"claude-3-5-sonnet-20240620": NaN,
|
|
"claude-3-opus-20240229": 0.35104669887278583,
|
|
"gemini-1.5-pro-api-0409-preview": NaN,
|
|
"gemini-1.5-pro-exp-0801": NaN,
|
|
"gemini-advanced-0514": NaN,
|
|
"gemini-pro-dev-api": 0.5,
|
|
"glm-4-0520": NaN,
|
|
"gpt-3.5-turbo-0314": NaN,
|
|
"gpt-4o-2024-05-13": NaN,
|
|
"gpt-4o-2024-08-06": NaN,
|
|
"gpt-4o-mini-2024-07-18": NaN,
|
|
"llama-2-70b-chat": 0.5535714285714286,
|
|
"llama-3.1-70b-instruct": NaN,
|
|
"nemotron-4-340b-instruct": NaN,
|
|
"yi-large-preview": NaN
|
|
},
|
|
"glm-4-0520": {
|
|
"athene-70b-0725": NaN,
|
|
"bard-jan-24-gemini-pro": NaN,
|
|
"chatgpt-4o-latest": NaN,
|
|
"claude-1": NaN,
|
|
"claude-2.0": NaN,
|
|
"claude-3-5-sonnet-20240620": 0.41992433795712486,
|
|
"claude-3-opus-20240229": 0.45756880733944955,
|
|
"gemini-1.5-pro-api-0409-preview": NaN,
|
|
"gemini-1.5-pro-exp-0801": NaN,
|
|
"gemini-advanced-0514": 0.4226618705035971,
|
|
"gemini-pro-dev-api": NaN,
|
|
"glm-4-0520": 0.5,
|
|
"gpt-3.5-turbo-0314": NaN,
|
|
"gpt-4o-2024-05-13": 0.3613861386138614,
|
|
"gpt-4o-2024-08-06": NaN,
|
|
"gpt-4o-mini-2024-07-18": NaN,
|
|
"llama-2-70b-chat": NaN,
|
|
"llama-3.1-70b-instruct": NaN,
|
|
"nemotron-4-340b-instruct": 0.5087025316455697,
|
|
"yi-large-preview": 0.448943661971831
|
|
},
|
|
"gpt-3.5-turbo-0314": {
|
|
"athene-70b-0725": NaN,
|
|
"bard-jan-24-gemini-pro": NaN,
|
|
"chatgpt-4o-latest": NaN,
|
|
"claude-1": 0.4451219512195122,
|
|
"claude-2.0": NaN,
|
|
"claude-3-5-sonnet-20240620": NaN,
|
|
"claude-3-opus-20240229": NaN,
|
|
"gemini-1.5-pro-api-0409-preview": NaN,
|
|
"gemini-1.5-pro-exp-0801": NaN,
|
|
"gemini-advanced-0514": NaN,
|
|
"gemini-pro-dev-api": NaN,
|
|
"glm-4-0520": NaN,
|
|
"gpt-3.5-turbo-0314": 0.5,
|
|
"gpt-4o-2024-05-13": NaN,
|
|
"gpt-4o-2024-08-06": NaN,
|
|
"gpt-4o-mini-2024-07-18": NaN,
|
|
"llama-2-70b-chat": NaN,
|
|
"llama-3.1-70b-instruct": NaN,
|
|
"nemotron-4-340b-instruct": NaN,
|
|
"yi-large-preview": NaN
|
|
},
|
|
"gpt-4o-2024-05-13": {
|
|
"athene-70b-0725": 0.5568760611205433,
|
|
"bard-jan-24-gemini-pro": NaN,
|
|
"chatgpt-4o-latest": 0.45579078455790784,
|
|
"claude-1": NaN,
|
|
"claude-2.0": NaN,
|
|
"claude-3-5-sonnet-20240620": 0.5212426978226234,
|
|
"claude-3-opus-20240229": 0.5518305661983823,
|
|
"gemini-1.5-pro-api-0409-preview": NaN,
|
|
"gemini-1.5-pro-exp-0801": 0.4770554493307839,
|
|
"gemini-advanced-0514": 0.5098219766728054,
|
|
"gemini-pro-dev-api": NaN,
|
|
"glm-4-0520": 0.6386138613861386,
|
|
"gpt-3.5-turbo-0314": NaN,
|
|
"gpt-4o-2024-05-13": 0.5,
|
|
"gpt-4o-2024-08-06": 0.544973544973545,
|
|
"gpt-4o-mini-2024-07-18": 0.5163472378804961,
|
|
"llama-2-70b-chat": 0.5607476635514018,
|
|
"llama-3.1-70b-instruct": 0.5650224215246636,
|
|
"nemotron-4-340b-instruct": 0.5968559837728195,
|
|
"yi-large-preview": 0.5756445047489823
|
|
},
|
|
"gpt-4o-2024-08-06": {
|
|
"athene-70b-0725": 0.494750656167979,
|
|
"bard-jan-24-gemini-pro": NaN,
|
|
"chatgpt-4o-latest": 0.4835164835164835,
|
|
"claude-1": NaN,
|
|
"claude-2.0": NaN,
|
|
"claude-3-5-sonnet-20240620": 0.4810126582278481,
|
|
"claude-3-opus-20240229": 0.5630372492836676,
|
|
"gemini-1.5-pro-api-0409-preview": NaN,
|
|
"gemini-1.5-pro-exp-0801": 0.4758928571428571,
|
|
"gemini-advanced-0514": NaN,
|
|
"gemini-pro-dev-api": NaN,
|
|
"glm-4-0520": NaN,
|
|
"gpt-3.5-turbo-0314": NaN,
|
|
"gpt-4o-2024-05-13": 0.455026455026455,
|
|
"gpt-4o-2024-08-06": 0.5,
|
|
"gpt-4o-mini-2024-07-18": 0.5052910052910053,
|
|
"llama-2-70b-chat": NaN,
|
|
"llama-3.1-70b-instruct": 0.5273037542662116,
|
|
"nemotron-4-340b-instruct": NaN,
|
|
"yi-large-preview": NaN
|
|
},
|
|
"gpt-4o-mini-2024-07-18": {
|
|
"athene-70b-0725": 0.5246212121212122,
|
|
"bard-jan-24-gemini-pro": NaN,
|
|
"chatgpt-4o-latest": 0.39892665474060823,
|
|
"claude-1": NaN,
|
|
"claude-2.0": NaN,
|
|
"claude-3-5-sonnet-20240620": 0.5251509054325956,
|
|
"claude-3-opus-20240229": 0.5562613430127041,
|
|
"gemini-1.5-pro-api-0409-preview": NaN,
|
|
"gemini-1.5-pro-exp-0801": 0.47044025157232705,
|
|
"gemini-advanced-0514": 0.5395927601809954,
|
|
"gemini-pro-dev-api": NaN,
|
|
"glm-4-0520": NaN,
|
|
"gpt-3.5-turbo-0314": NaN,
|
|
"gpt-4o-2024-05-13": 0.4836527621195039,
|
|
"gpt-4o-2024-08-06": 0.4947089947089947,
|
|
"gpt-4o-mini-2024-07-18": 0.5,
|
|
"llama-2-70b-chat": NaN,
|
|
"llama-3.1-70b-instruct": 0.5584756898817346,
|
|
"nemotron-4-340b-instruct": NaN,
|
|
"yi-large-preview": 0.553125
|
|
},
|
|
"llama-2-70b-chat": {
|
|
"athene-70b-0725": NaN,
|
|
"bard-jan-24-gemini-pro": 0.35074626865671643,
|
|
"chatgpt-4o-latest": NaN,
|
|
"claude-1": 0.396,
|
|
"claude-2.0": 0.41331658291457285,
|
|
"claude-3-5-sonnet-20240620": NaN,
|
|
"claude-3-opus-20240229": 0.3109048723897912,
|
|
"gemini-1.5-pro-api-0409-preview": 0.3125,
|
|
"gemini-1.5-pro-exp-0801": NaN,
|
|
"gemini-advanced-0514": 0.3854166666666667,
|
|
"gemini-pro-dev-api": 0.44642857142857145,
|
|
"glm-4-0520": NaN,
|
|
"gpt-3.5-turbo-0314": NaN,
|
|
"gpt-4o-2024-05-13": 0.4392523364485981,
|
|
"gpt-4o-2024-08-06": NaN,
|
|
"gpt-4o-mini-2024-07-18": NaN,
|
|
"llama-2-70b-chat": 0.5,
|
|
"llama-3.1-70b-instruct": NaN,
|
|
"nemotron-4-340b-instruct": NaN,
|
|
"yi-large-preview": 0.42142857142857143
|
|
},
|
|
"llama-3.1-70b-instruct": {
|
|
"athene-70b-0725": 0.46825396825396826,
|
|
"bard-jan-24-gemini-pro": NaN,
|
|
"chatgpt-4o-latest": 0.4206161137440758,
|
|
"claude-1": NaN,
|
|
"claude-2.0": NaN,
|
|
"claude-3-5-sonnet-20240620": 0.461038961038961,
|
|
"claude-3-opus-20240229": 0.5186480186480187,
|
|
"gemini-1.5-pro-api-0409-preview": NaN,
|
|
"gemini-1.5-pro-exp-0801": 0.4226907630522088,
|
|
"gemini-advanced-0514": 0.4576923076923077,
|
|
"gemini-pro-dev-api": NaN,
|
|
"glm-4-0520": NaN,
|
|
"gpt-3.5-turbo-0314": NaN,
|
|
"gpt-4o-2024-05-13": 0.4349775784753363,
|
|
"gpt-4o-2024-08-06": 0.4726962457337884,
|
|
"gpt-4o-mini-2024-07-18": 0.44152431011826543,
|
|
"llama-2-70b-chat": NaN,
|
|
"llama-3.1-70b-instruct": 0.5,
|
|
"nemotron-4-340b-instruct": NaN,
|
|
"yi-large-preview": 0.58
|
|
},
|
|
"nemotron-4-340b-instruct": {
|
|
"athene-70b-0725": NaN,
|
|
"bard-jan-24-gemini-pro": NaN,
|
|
"chatgpt-4o-latest": NaN,
|
|
"claude-1": NaN,
|
|
"claude-2.0": NaN,
|
|
"claude-3-5-sonnet-20240620": 0.4101642710472279,
|
|
"claude-3-opus-20240229": 0.45686900958466453,
|
|
"gemini-1.5-pro-api-0409-preview": NaN,
|
|
"gemini-1.5-pro-exp-0801": NaN,
|
|
"gemini-advanced-0514": 0.4192592592592593,
|
|
"gemini-pro-dev-api": NaN,
|
|
"glm-4-0520": 0.4912974683544304,
|
|
"gpt-3.5-turbo-0314": NaN,
|
|
"gpt-4o-2024-05-13": 0.40314401622718055,
|
|
"gpt-4o-2024-08-06": NaN,
|
|
"gpt-4o-mini-2024-07-18": NaN,
|
|
"llama-2-70b-chat": NaN,
|
|
"llama-3.1-70b-instruct": NaN,
|
|
"nemotron-4-340b-instruct": 0.5,
|
|
"yi-large-preview": 0.44568690095846647
|
|
},
|
|
"yi-large-preview": {
|
|
"athene-70b-0725": 0.47058823529411764,
|
|
"bard-jan-24-gemini-pro": NaN,
|
|
"chatgpt-4o-latest": NaN,
|
|
"claude-1": NaN,
|
|
"claude-2.0": NaN,
|
|
"claude-3-5-sonnet-20240620": 0.4794238683127572,
|
|
"claude-3-opus-20240229": 0.47618094475580464,
|
|
"gemini-1.5-pro-api-0409-preview": NaN,
|
|
"gemini-1.5-pro-exp-0801": 0.41379310344827586,
|
|
"gemini-advanced-0514": 0.4397363465160075,
|
|
"gemini-pro-dev-api": NaN,
|
|
"glm-4-0520": 0.551056338028169,
|
|
"gpt-3.5-turbo-0314": NaN,
|
|
"gpt-4o-2024-05-13": 0.4243554952510176,
|
|
"gpt-4o-2024-08-06": NaN,
|
|
"gpt-4o-mini-2024-07-18": 0.446875,
|
|
"llama-2-70b-chat": 0.5785714285714286,
|
|
"llama-3.1-70b-instruct": 0.42,
|
|
"nemotron-4-340b-instruct": 0.5543130990415336,
|
|
"yi-large-preview": 0.5
|
|
}
|
|
},
|
|
"models": [
|
|
"gemini-1.5-pro-api-0409-preview",
|
|
"gemini-1.5-pro-exp-0801",
|
|
"chatgpt-4o-latest",
|
|
"gpt-3.5-turbo-0314",
|
|
"bard-jan-24-gemini-pro",
|
|
"claude-1",
|
|
"gemini-advanced-0514",
|
|
"llama-3.1-70b-instruct",
|
|
"gpt-4o-2024-05-13",
|
|
"gpt-4o-2024-08-06",
|
|
"gpt-4o-mini-2024-07-18",
|
|
"claude-3-5-sonnet-20240620",
|
|
"claude-3-opus-20240229",
|
|
"athene-70b-0725",
|
|
"gemini-pro-dev-api",
|
|
"claude-2.0",
|
|
"glm-4-0520",
|
|
"nemotron-4-340b-instruct",
|
|
"yi-large-preview",
|
|
"llama-2-70b-chat"
|
|
],
|
|
"online_elo_predicted": {
|
|
"athene-70b-0725": {
|
|
"athene-70b-0725": 0.5,
|
|
"bard-jan-24-gemini-pro": 0.4706024381703526,
|
|
"chatgpt-4o-latest": 0.4244076072370654,
|
|
"claude-1": 0.4727267496028405,
|
|
"claude-2.0": 0.5060871587475949,
|
|
"claude-3-5-sonnet-20240620": 0.4924467854859755,
|
|
"claude-3-opus-20240229": 0.4983492492034077,
|
|
"gemini-1.5-pro-api-0409-preview": 0.3786225197416955,
|
|
"gemini-1.5-pro-exp-0801": 0.4227290744565508,
|
|
"gemini-advanced-0514": 0.48017931822260296,
|
|
"gemini-pro-dev-api": 0.5020917941129024,
|
|
"glm-4-0520": 0.5121782721655728,
|
|
"gpt-3.5-turbo-0314": 0.45662732701186726,
|
|
"gpt-4o-2024-05-13": 0.4813526553622729,
|
|
"gpt-4o-2024-08-06": 0.482966766553394,
|
|
"gpt-4o-mini-2024-07-18": 0.492191613318456,
|
|
"llama-2-70b-chat": 0.5188804447839834,
|
|
"llama-3.1-70b-instruct": 0.4804491928529648,
|
|
"nemotron-4-340b-instruct": 0.5140723365206418,
|
|
"yi-large-preview": 0.5185627002158419
|
|
},
|
|
"bard-jan-24-gemini-pro": {
|
|
"athene-70b-0725": 0.5293975618296474,
|
|
"bard-jan-24-gemini-pro": 0.5,
|
|
"chatgpt-4o-latest": 0.45339086380344346,
|
|
"claude-1": 0.5021311461637057,
|
|
"claude-2.0": 0.5354593391190725,
|
|
"claude-3-5-sonnet-20240620": 0.5218637663710245,
|
|
"claude-3-opus-20240229": 0.5277521980731233,
|
|
"gemini-1.5-pro-api-0409-preview": 0.4066882610443156,
|
|
"gemini-1.5-pro-exp-0801": 0.45168765548015544,
|
|
"gemini-advanced-0514": 0.5095992532128728,
|
|
"gemini-pro-dev-api": 0.5314816122659721,
|
|
"glm-4-0520": 0.54151638062692,
|
|
"gpt-3.5-turbo-0314": 0.48595324754769137,
|
|
"gpt-4o-2024-05-13": 0.5107738414883239,
|
|
"gpt-4o-2024-08-06": 0.5123891431197954,
|
|
"gpt-4o-mini-2024-07-18": 0.5216090163334262,
|
|
"llama-2-70b-chat": 0.5481710593389454,
|
|
"llama-3.1-70b-instruct": 0.5098694443797749,
|
|
"nemotron-4-340b-instruct": 0.5433980845222826,
|
|
"yi-large-preview": 0.5478558027577041
|
|
},
|
|
"chatgpt-4o-latest": {
|
|
"athene-70b-0725": 0.5755923927629346,
|
|
"bard-jan-24-gemini-pro": 0.5466091361965566,
|
|
"chatgpt-4o-latest": 0.5,
|
|
"claude-1": 0.5487209243907352,
|
|
"claude-2.0": 0.5815294906471586,
|
|
"claude-3-5-sonnet-20240620": 0.5681949260650095,
|
|
"claude-3-opus-20240229": 0.5739785673924995,
|
|
"gemini-1.5-pro-api-0409-preview": 0.45247054063006786,
|
|
"gemini-1.5-pro-exp-0801": 0.49828131112534013,
|
|
"gemini-advanced-0514": 0.5561079756808931,
|
|
"gemini-pro-dev-api": 0.5776350830826076,
|
|
"glm-4-0520": 0.587448649362509,
|
|
"gpt-3.5-turbo-0314": 0.5326478829339771,
|
|
"gpt-4o-2024-05-13": 0.5572679471226406,
|
|
"gpt-4o-2024-08-06": 0.5588623197754942,
|
|
"gpt-4o-mini-2024-07-18": 0.5679444241258642,
|
|
"llama-2-70b-chat": 0.5939365657179976,
|
|
"llama-3.1-70b-instruct": 0.5563748494378427,
|
|
"nemotron-4-340b-instruct": 0.5892848182429368,
|
|
"yi-large-preview": 0.5936295693344523
|
|
},
|
|
"claude-1": {
|
|
"athene-70b-0725": 0.5272732503971594,
|
|
"bard-jan-24-gemini-pro": 0.4978688538362943,
|
|
"chatgpt-4o-latest": 0.45127907560926495,
|
|
"claude-1": 0.5,
|
|
"claude-2.0": 0.5333382703189705,
|
|
"claude-3-5-sonnet-20240620": 0.5197362986493318,
|
|
"claude-3-opus-20240229": 0.5256271146687194,
|
|
"gemini-1.5-pro-api-0409-preview": 0.4046329739918908,
|
|
"gemini-1.5-pro-exp-0801": 0.44957727554595445,
|
|
"gemini-advanced-0514": 0.5074687182117393,
|
|
"gemini-pro-dev-api": 0.5293583449328568,
|
|
"glm-4-0520": 0.539399178222487,
|
|
"gpt-3.5-turbo-0314": 0.483824038337802,
|
|
"gpt-4o-2024-05-13": 0.5086434891644779,
|
|
"gpt-4o-2024-08-06": 0.5102590804411641,
|
|
"gpt-4o-mini-2024-07-18": 0.519481458808123,
|
|
"llama-2-70b-chat": 0.5460588266923004,
|
|
"llama-3.1-70b-instruct": 0.5077389493164274,
|
|
"nemotron-4-340b-instruct": 0.541282210739082,
|
|
"yi-large-preview": 0.5457433176189294
|
|
},
|
|
"claude-2.0": {
|
|
"athene-70b-0725": 0.4939128412524052,
|
|
"bard-jan-24-gemini-pro": 0.46454066088092755,
|
|
"chatgpt-4o-latest": 0.41847050935284147,
|
|
"claude-1": 0.46666172968102954,
|
|
"claude-2.0": 0.5,
|
|
"claude-3-5-sonnet-20240620": 0.4863621348844711,
|
|
"claude-3-opus-20240229": 0.4922624014572012,
|
|
"gemini-1.5-pro-api-0409-preview": 0.3729109568972296,
|
|
"gemini-1.5-pro-exp-0801": 0.41679845455453196,
|
|
"gemini-advanced-0514": 0.474104656737174,
|
|
"gemini-pro-dev-api": 0.4960044318617072,
|
|
"glm-4-0520": 0.5060929201168735,
|
|
"gpt-3.5-turbo-0314": 0.4505923459773481,
|
|
"gpt-4o-2024-05-13": 0.4752767219072891,
|
|
"gpt-4o-2024-08-06": 0.4768891926892078,
|
|
"gpt-4o-mini-2024-07-18": 0.4861070959392006,
|
|
"llama-2-70b-chat": 0.5127991699819673,
|
|
"llama-3.1-70b-instruct": 0.47437423287938824,
|
|
"nemotron-4-340b-instruct": 0.5079879147696204,
|
|
"yi-large-preview": 0.512481182668407
|
|
},
|
|
"claude-3-5-sonnet-20240620": {
|
|
"athene-70b-0725": 0.5075532145140246,
|
|
"bard-jan-24-gemini-pro": 0.4781362336289755,
|
|
"chatgpt-4o-latest": 0.4318050739349906,
|
|
"claude-1": 0.4802637013506682,
|
|
"claude-2.0": 0.5136378651155289,
|
|
"claude-3-5-sonnet-20240620": 0.5,
|
|
"claude-3-opus-20240229": 0.505902758110997,
|
|
"gemini-1.5-pro-api-0409-preview": 0.38575678604471353,
|
|
"gemini-1.5-pro-exp-0801": 0.4301191468425039,
|
|
"gemini-advanced-0514": 0.4877251820914822,
|
|
"gemini-pro-dev-api": 0.5096443991097894,
|
|
"glm-4-0520": 0.519724229338601,
|
|
"gpt-3.5-turbo-0314": 0.46413354167370846,
|
|
"gpt-4o-2024-05-13": 0.48889961603567494,
|
|
"gpt-4o-2024-08-06": 0.4905150999228697,
|
|
"gpt-4o-mini-2024-07-18": 0.49974476761967085,
|
|
"llama-2-70b-chat": 0.526418589284047,
|
|
"llama-3.1-70b-instruct": 0.487995316371302,
|
|
"nemotron-4-340b-instruct": 0.5216163605038188,
|
|
"yi-large-preview": 0.5261012762929619
|
|
},
|
|
"claude-3-opus-20240229": {
|
|
"athene-70b-0725": 0.5016507507965924,
|
|
"bard-jan-24-gemini-pro": 0.47224780192687665,
|
|
"chatgpt-4o-latest": 0.4260214326075004,
|
|
"claude-1": 0.47437288533128064,
|
|
"claude-2.0": 0.5077375985427988,
|
|
"claude-3-5-sonnet-20240620": 0.49409724188900295,
|
|
"claude-3-opus-20240229": 0.5,
|
|
"gemini-1.5-pro-api-0409-preview": 0.3801772378799626,
|
|
"gemini-1.5-pro-exp-0801": 0.4243412226190692,
|
|
"gemini-advanced-0514": 0.4818276906995902,
|
|
"gemini-pro-dev-api": 0.5037424932177174,
|
|
"glm-4-0520": 0.513827911016007,
|
|
"gpt-3.5-turbo-0314": 0.4582661256484433,
|
|
"gpt-4o-2024-05-13": 0.4830013131364567,
|
|
"gpt-4o-2024-08-06": 0.48461578707994823,
|
|
"gpt-4o-mini-2024-07-18": 0.4938420466183484,
|
|
"llama-2-70b-chat": 0.520528636323993,
|
|
"llama-3.1-70b-instruct": 0.48209763256058513,
|
|
"nemotron-4-340b-instruct": 0.5157216264686881,
|
|
"yi-large-preview": 0.5202109737620978
|
|
},
|
|
"gemini-1.5-pro-api-0409-preview": {
|
|
"athene-70b-0725": 0.6213774802583045,
|
|
"bard-jan-24-gemini-pro": 0.5933117389556843,
|
|
"chatgpt-4o-latest": 0.5475294593699321,
|
|
"claude-1": 0.5953670260081093,
|
|
"claude-2.0": 0.6270890431027705,
|
|
"claude-3-5-sonnet-20240620": 0.6142432139552865,
|
|
"claude-3-opus-20240229": 0.6198227621200374,
|
|
"gemini-1.5-pro-api-0409-preview": 0.5,
|
|
"gemini-1.5-pro-exp-0801": 0.5458257442135583,
|
|
"gemini-advanced-0514": 0.6025435895577902,
|
|
"gemini-pro-dev-api": 0.6233440078256695,
|
|
"glm-4-0520": 0.6327707226950309,
|
|
"gpt-3.5-turbo-0314": 0.579682755828864,
|
|
"gpt-4o-2024-05-13": 0.6036686971453942,
|
|
"gpt-4o-2024-08-06": 0.6052143488362124,
|
|
"gpt-4o-mini-2024-07-18": 0.6140012780307695,
|
|
"llama-2-70b-chat": 0.6389839091289585,
|
|
"llama-3.1-70b-instruct": 0.6028024856995498,
|
|
"nemotron-4-340b-instruct": 0.6345306684098833,
|
|
"yi-large-preview": 0.6386902518991052
|
|
},
|
|
"gemini-1.5-pro-exp-0801": {
|
|
"athene-70b-0725": 0.5772709255434492,
|
|
"bard-jan-24-gemini-pro": 0.5483123445198447,
|
|
"chatgpt-4o-latest": 0.5017186888746599,
|
|
"claude-1": 0.5504227244540455,
|
|
"claude-2.0": 0.5832015454454681,
|
|
"claude-3-5-sonnet-20240620": 0.569880853157496,
|
|
"claude-3-opus-20240229": 0.5756587773809309,
|
|
"gemini-1.5-pro-api-0409-preview": 0.4541742557864416,
|
|
"gemini-1.5-pro-exp-0801": 0.5,
|
|
"gemini-advanced-0514": 0.557804367756876,
|
|
"gemini-pro-dev-api": 0.5793114416789945,
|
|
"glm-4-0520": 0.5891137641041534,
|
|
"gpt-3.5-turbo-0314": 0.5343588600926158,
|
|
"gpt-4o-2024-05-13": 0.5589634219132797,
|
|
"gpt-4o-2024-08-06": 0.5605565036097535,
|
|
"gpt-4o-mini-2024-07-18": 0.5696305884618997,
|
|
"llama-2-70b-chat": 0.5955935211645167,
|
|
"llama-3.1-70b-instruct": 0.5580710321113055,
|
|
"nemotron-4-340b-instruct": 0.5909476824028691,
|
|
"yi-large-preview": 0.5952869238841539
|
|
},
|
|
"gemini-advanced-0514": {
|
|
"athene-70b-0725": 0.519820681777397,
|
|
"bard-jan-24-gemini-pro": 0.49040074678712725,
|
|
"chatgpt-4o-latest": 0.4438920243191068,
|
|
"claude-1": 0.4925312817882607,
|
|
"claude-2.0": 0.525895343262826,
|
|
"claude-3-5-sonnet-20240620": 0.5122748179085177,
|
|
"claude-3-opus-20240229": 0.5181723093004097,
|
|
"gemini-1.5-pro-api-0409-preview": 0.3974564104422098,
|
|
"gemini-1.5-pro-exp-0801": 0.44219563224312397,
|
|
"gemini-advanced-0514": 0.5,
|
|
"gemini-pro-dev-api": 0.5219088424590324,
|
|
"glm-4-0520": 0.5319680879028288,
|
|
"gpt-3.5-turbo-0314": 0.4763667410118573,
|
|
"gpt-4o-2024-05-13": 0.5011750743841354,
|
|
"gpt-4o-2024-08-06": 0.5027912177061772,
|
|
"gpt-4o-mini-2024-07-18": 0.5120197361562043,
|
|
"llama-2-70b-chat": 0.5386432816976552,
|
|
"llama-3.1-70b-instruct": 0.5002702935966019,
|
|
"nemotron-4-340b-instruct": 0.5338552462294891,
|
|
"yi-large-preview": 0.5383269761251527
|
|
},
|
|
"gemini-pro-dev-api": {
|
|
"athene-70b-0725": 0.4979082058870976,
|
|
"bard-jan-24-gemini-pro": 0.4685183877340279,
|
|
"chatgpt-4o-latest": 0.4223649169173924,
|
|
"claude-1": 0.47064165506714317,
|
|
"claude-2.0": 0.5039955681382927,
|
|
"claude-3-5-sonnet-20240620": 0.4903556008902106,
|
|
"claude-3-opus-20240229": 0.4962575067822826,
|
|
"gemini-1.5-pro-api-0409-preview": 0.37665599217433055,
|
|
"gemini-1.5-pro-exp-0801": 0.4206885583210056,
|
|
"gemini-advanced-0514": 0.4780911575409677,
|
|
"gemini-pro-dev-api": 0.5,
|
|
"glm-4-0520": 0.5100875059468505,
|
|
"gpt-3.5-turbo-0314": 0.45455202627804153,
|
|
"gpt-4o-2024-05-13": 0.47926409658161856,
|
|
"gpt-4o-2024-08-06": 0.4808776977523424,
|
|
"gpt-4o-mini-2024-07-18": 0.49010046598318574,
|
|
"llama-2-70b-chat": 0.5167913032942285,
|
|
"llama-3.1-70b-instruct": 0.4783609385670775,
|
|
"nemotron-4-340b-instruct": 0.5119819532314825,
|
|
"yi-large-preview": 0.516473464718453
|
|
},
|
|
"glm-4-0520": {
|
|
"athene-70b-0725": 0.4878217278344273,
|
|
"bard-jan-24-gemini-pro": 0.4584836193730801,
|
|
"chatgpt-4o-latest": 0.41255135063749104,
|
|
"claude-1": 0.4606008217775131,
|
|
"claude-2.0": 0.49390707988312654,
|
|
"claude-3-5-sonnet-20240620": 0.48027577066139915,
|
|
"claude-3-opus-20240229": 0.48617208898399294,
|
|
"gemini-1.5-pro-api-0409-preview": 0.3672292773049691,
|
|
"gemini-1.5-pro-exp-0801": 0.4108862358958465,
|
|
"gemini-advanced-0514": 0.4680319120971712,
|
|
"gemini-pro-dev-api": 0.4899124940531495,
|
|
"glm-4-0520": 0.5,
|
|
"gpt-3.5-turbo-0314": 0.444566176363753,
|
|
"gpt-4o-2024-05-13": 0.4692023588423809,
|
|
"gpt-4o-2024-08-06": 0.47081271228911237,
|
|
"gpt-4o-mini-2024-07-18": 0.4800209406003484,
|
|
"llama-2-70b-chat": 0.5067083424471972,
|
|
"llama-3.1-70b-instruct": 0.4683011100825741,
|
|
"nemotron-4-340b-instruct": 0.5018953636400675,
|
|
"yi-large-preview": 0.5063902063717687
|
|
},
|
|
"gpt-3.5-turbo-0314": {
|
|
"athene-70b-0725": 0.5433726729881329,
|
|
"bard-jan-24-gemini-pro": 0.5140467524523086,
|
|
"chatgpt-4o-latest": 0.4673521170660229,
|
|
"claude-1": 0.5161759616621979,
|
|
"claude-2.0": 0.5494076540226519,
|
|
"claude-3-5-sonnet-20240620": 0.5358664583262915,
|
|
"claude-3-opus-20240229": 0.5417338743515567,
|
|
"gemini-1.5-pro-api-0409-preview": 0.4203172441711361,
|
|
"gemini-1.5-pro-exp-0801": 0.4656411399073841,
|
|
"gemini-advanced-0514": 0.5236332589881427,
|
|
"gemini-pro-dev-api": 0.5454479737219585,
|
|
"glm-4-0520": 0.5554338236362469,
|
|
"gpt-3.5-turbo-0314": 0.5,
|
|
"gpt-4o-2024-05-13": 0.5248055778856127,
|
|
"gpt-4o-2024-08-06": 0.5264175061108259,
|
|
"gpt-4o-mini-2024-07-18": 0.5356125299744643,
|
|
"llama-2-70b-chat": 0.5620498683755348,
|
|
"llama-3.1-70b-instruct": 0.5239029418245605,
|
|
"nemotron-4-340b-instruct": 0.5573051037168208,
|
|
"yi-large-preview": 0.5617365533684751
|
|
},
|
|
"gpt-4o-2024-05-13": {
|
|
"athene-70b-0725": 0.5186473446377271,
|
|
"bard-jan-24-gemini-pro": 0.48922615851167606,
|
|
"chatgpt-4o-latest": 0.4427320528773593,
|
|
"claude-1": 0.49135651083552223,
|
|
"claude-2.0": 0.5247232780927109,
|
|
"claude-3-5-sonnet-20240620": 0.511100383964325,
|
|
"claude-3-opus-20240229": 0.5169986868635432,
|
|
"gemini-1.5-pro-api-0409-preview": 0.3963313028546058,
|
|
"gemini-1.5-pro-exp-0801": 0.44103657808672025,
|
|
"gemini-advanced-0514": 0.4988249256158645,
|
|
"gemini-pro-dev-api": 0.5207359034183815,
|
|
"glm-4-0520": 0.5307976411576192,
|
|
"gpt-3.5-turbo-0314": 0.4751944221143874,
|
|
"gpt-4o-2024-05-13": 0.5,
|
|
"gpt-4o-2024-08-06": 0.501616164525399,
|
|
"gpt-4o-mini-2024-07-18": 0.5108452744903431,
|
|
"llama-2-70b-chat": 0.5374750140847713,
|
|
"llama-3.1-70b-instruct": 0.4990952180629769,
|
|
"nemotron-4-340b-instruct": 0.5326853730599583,
|
|
"yi-large-preview": 0.537158595794847
|
|
},
|
|
"gpt-4o-2024-08-06": {
|
|
"athene-70b-0725": 0.517033233446606,
|
|
"bard-jan-24-gemini-pro": 0.48761085688020456,
|
|
"chatgpt-4o-latest": 0.44113768022450583,
|
|
"claude-1": 0.4897409195588359,
|
|
"claude-2.0": 0.5231108073107922,
|
|
"claude-3-5-sonnet-20240620": 0.5094849000771304,
|
|
"claude-3-opus-20240229": 0.5153842129200518,
|
|
"gemini-1.5-pro-api-0409-preview": 0.39478565116378755,
|
|
"gemini-1.5-pro-exp-0801": 0.4394434963902465,
|
|
"gemini-advanced-0514": 0.4972087822938228,
|
|
"gemini-pro-dev-api": 0.5191223022476575,
|
|
"glm-4-0520": 0.5291872877108876,
|
|
"gpt-3.5-turbo-0314": 0.473582493889174,
|
|
"gpt-4o-2024-05-13": 0.4983838354746009,
|
|
"gpt-4o-2024-08-06": 0.5,
|
|
"gpt-4o-mini-2024-07-18": 0.5092297570723646,
|
|
"llama-2-70b-chat": 0.5358675389424615,
|
|
"llama-3.1-70b-instruct": 0.49747906828277433,
|
|
"nemotron-4-340b-instruct": 0.531075774838379,
|
|
"yi-large-preview": 0.5355509712390535
|
|
},
|
|
"gpt-4o-mini-2024-07-18": {
|
|
"athene-70b-0725": 0.507808386681544,
|
|
"bard-jan-24-gemini-pro": 0.47839098366657384,
|
|
"chatgpt-4o-latest": 0.43205557587413584,
|
|
"claude-1": 0.48051854119187704,
|
|
"claude-2.0": 0.5138929040607993,
|
|
"claude-3-5-sonnet-20240620": 0.5002552323803292,
|
|
"claude-3-opus-20240229": 0.5061579533816516,
|
|
"gemini-1.5-pro-api-0409-preview": 0.38599872196923046,
|
|
"gemini-1.5-pro-exp-0801": 0.4303694115381003,
|
|
"gemini-advanced-0514": 0.4879802638437957,
|
|
"gemini-pro-dev-api": 0.5098995340168142,
|
|
"glm-4-0520": 0.5199790593996516,
|
|
"gpt-3.5-turbo-0314": 0.4643874700255357,
|
|
"gpt-4o-2024-05-13": 0.4891547255096569,
|
|
"gpt-4o-2024-08-06": 0.4907702429276354,
|
|
"gpt-4o-mini-2024-07-18": 0.5,
|
|
"llama-2-70b-chat": 0.5266731022503263,
|
|
"llama-3.1-70b-instruct": 0.4882504047493449,
|
|
"nemotron-4-340b-instruct": 0.5218711102154154,
|
|
"yi-large-preview": 0.5263558063552674
|
|
},
|
|
"llama-2-70b-chat": {
|
|
"athene-70b-0725": 0.4811195552160165,
|
|
"bard-jan-24-gemini-pro": 0.4518289406610546,
|
|
"chatgpt-4o-latest": 0.40606343428200253,
|
|
"claude-1": 0.4539411733076995,
|
|
"claude-2.0": 0.4872008300180327,
|
|
"claude-3-5-sonnet-20240620": 0.4735814107159531,
|
|
"claude-3-opus-20240229": 0.4794713636760069,
|
|
"gemini-1.5-pro-api-0409-preview": 0.3610160908710415,
|
|
"gemini-1.5-pro-exp-0801": 0.40440647883548325,
|
|
"gemini-advanced-0514": 0.4613567183023448,
|
|
"gemini-pro-dev-api": 0.4832086967057715,
|
|
"glm-4-0520": 0.4932916575528028,
|
|
"gpt-3.5-turbo-0314": 0.43795013162446517,
|
|
"gpt-4o-2024-05-13": 0.4625249859152287,
|
|
"gpt-4o-2024-08-06": 0.46413246105753847,
|
|
"gpt-4o-mini-2024-07-18": 0.47332689774967374,
|
|
"llama-2-70b-chat": 0.5,
|
|
"llama-3.1-70b-instruct": 0.46162540860366846,
|
|
"nemotron-4-340b-instruct": 0.49518677639716263,
|
|
"yi-large-preview": 0.49968180936417794
|
|
},
|
|
"llama-3.1-70b-instruct": {
|
|
"athene-70b-0725": 0.5195508071470352,
|
|
"bard-jan-24-gemini-pro": 0.4901305556202252,
|
|
"chatgpt-4o-latest": 0.4436251505621573,
|
|
"claude-1": 0.4922610506835726,
|
|
"claude-2.0": 0.5256257671206118,
|
|
"claude-3-5-sonnet-20240620": 0.512004683628698,
|
|
"claude-3-opus-20240229": 0.5179023674394149,
|
|
"gemini-1.5-pro-api-0409-preview": 0.3971975143004503,
|
|
"gemini-1.5-pro-exp-0801": 0.4419289678886945,
|
|
"gemini-advanced-0514": 0.49972970640339814,
|
|
"gemini-pro-dev-api": 0.5216390614329225,
|
|
"glm-4-0520": 0.531698889917426,
|
|
"gpt-3.5-turbo-0314": 0.47609705817543935,
|
|
"gpt-4o-2024-05-13": 0.5009047819370231,
|
|
"gpt-4o-2024-08-06": 0.5025209317172257,
|
|
"gpt-4o-mini-2024-07-18": 0.5117495952506551,
|
|
"llama-2-70b-chat": 0.5383745913963316,
|
|
"llama-3.1-70b-instruct": 0.5,
|
|
"nemotron-4-340b-instruct": 0.5335861820021834,
|
|
"yi-large-preview": 0.5380582595922262
|
|
},
|
|
"nemotron-4-340b-instruct": {
|
|
"athene-70b-0725": 0.4859276634793583,
|
|
"bard-jan-24-gemini-pro": 0.45660191547771745,
|
|
"chatgpt-4o-latest": 0.4107151817570633,
|
|
"claude-1": 0.458717789260918,
|
|
"claude-2.0": 0.4920120852303797,
|
|
"claude-3-5-sonnet-20240620": 0.47838363949618123,
|
|
"claude-3-opus-20240229": 0.4842783735313118,
|
|
"gemini-1.5-pro-api-0409-preview": 0.3654693315901167,
|
|
"gemini-1.5-pro-exp-0801": 0.4090523175971309,
|
|
"gemini-advanced-0514": 0.4661447537705109,
|
|
"gemini-pro-dev-api": 0.4880180467685175,
|
|
"glm-4-0520": 0.49810463635993246,
|
|
"gpt-3.5-turbo-0314": 0.4426948962831791,
|
|
"gpt-4o-2024-05-13": 0.4673146269400416,
|
|
"gpt-4o-2024-08-06": 0.46892422516162097,
|
|
"gpt-4o-mini-2024-07-18": 0.47812888978458457,
|
|
"llama-2-70b-chat": 0.5048132236028374,
|
|
"llama-3.1-70b-instruct": 0.4664138179978165,
|
|
"nemotron-4-340b-instruct": 0.5,
|
|
"yi-large-preview": 0.5044950605041638
|
|
},
|
|
"yi-large-preview": {
|
|
"athene-70b-0725": 0.48143729978415806,
|
|
"bard-jan-24-gemini-pro": 0.4521441972422958,
|
|
"chatgpt-4o-latest": 0.4063704306655477,
|
|
"claude-1": 0.45425668238107064,
|
|
"claude-2.0": 0.48751881733159297,
|
|
"claude-3-5-sonnet-20240620": 0.4738987237070381,
|
|
"claude-3-opus-20240229": 0.47978902623790215,
|
|
"gemini-1.5-pro-api-0409-preview": 0.3613097481008948,
|
|
"gemini-1.5-pro-exp-0801": 0.40471307611584606,
|
|
"gemini-advanced-0514": 0.4616730238748474,
|
|
"gemini-pro-dev-api": 0.48352653528154693,
|
|
"glm-4-0520": 0.4936097936282313,
|
|
"gpt-3.5-turbo-0314": 0.4382634466315249,
|
|
"gpt-4o-2024-05-13": 0.462841404205153,
|
|
"gpt-4o-2024-08-06": 0.46444902876094657,
|
|
"gpt-4o-mini-2024-07-18": 0.4736441936447327,
|
|
"llama-2-70b-chat": 0.5003181906358221,
|
|
"llama-3.1-70b-instruct": 0.4619417404077737,
|
|
"nemotron-4-340b-instruct": 0.4955049394958363,
|
|
"yi-large-preview": 0.5
|
|
}
|
|
}
|
|
}
|