languagebench / results.json
David Pomerenke
Nice tables and plots
a65282b
raw
history blame
12.4 kB
[
{
"language_name": "English",
"language_code": "eng",
"speakers": 1132366680.0,
"scores": [
{
"model": "openai/gpt-4o-mini",
"bleu": 0.47104084248165595
},
{
"model": "meta-llama/llama-3.3-70b-instruct",
"bleu": 0.4207265890491719
},
{
"model": "mistralai/mistral-small-24b-instruct-2501",
"bleu": 0.4642719176436136
},
{
"model": "google/gemini-2.0-flash-001",
"bleu": 0.5237470882988915
},
{
"model": "deepseek/deepseek-chat",
"bleu": 0.516570670982587
},
{
"model": "microsoft/phi-4",
"bleu": 0.44668905281921456
}
],
"bleu": 0.47384102687918905
},
{
"language_name": "Mandarin Chinese",
"language_code": "cmn",
"speakers": 1074000000.0,
"scores": [
{
"model": "meta-llama/llama-3.3-70b-instruct",
"bleu": 0.48254866511762295
}
],
"bleu": 0.48254866511762295
},
{
"language_name": "Spanish",
"language_code": "spa",
"speakers": 485000000.0,
"scores": [
{
"model": "meta-llama/llama-3.3-70b-instruct",
"bleu": 0.31606621368361204
}
],
"bleu": 0.31606621368361204
},
{
"language_name": "Hindi",
"language_code": "hin",
"speakers": 341000000.0,
"scores": [
{
"model": "meta-llama/llama-3.3-70b-instruct",
"bleu": 0.3273225856613046
}
],
"bleu": 0.3273225856613046
},
{
"language_name": "Bengali",
"language_code": "ben",
"speakers": 300000000.0,
"scores": [
{
"model": "meta-llama/llama-3.3-70b-instruct",
"bleu": 0.23110496173302814
}
],
"bleu": 0.23110496173302814
},
{
"language_name": "Portuguese",
"language_code": "por",
"speakers": 254300000.0,
"scores": [
{
"model": "meta-llama/llama-3.3-70b-instruct",
"bleu": 0.35032125995743685
}
],
"bleu": 0.35032125995743685
},
{
"language_name": "French",
"language_code": "fra",
"speakers": 208157220.0,
"scores": [
{
"model": "meta-llama/llama-3.3-70b-instruct",
"bleu": 0.31625053573185663
}
],
"bleu": 0.31625053573185663
},
{
"language_name": "Indonesian",
"language_code": "ind",
"speakers": 198996550.0,
"scores": [
{
"model": "meta-llama/llama-3.3-70b-instruct",
"bleu": 0.3112185444311794
}
],
"bleu": 0.3112185444311794
},
{
"language_name": "Russian",
"language_code": "rus",
"speakers": 171428900.0,
"scores": [
{
"model": "openai/gpt-4o-mini",
"bleu": 0.32615858913589074
},
{
"model": "meta-llama/llama-3.3-70b-instruct",
"bleu": 0.3244999119385425
},
{
"model": "mistralai/mistral-small-24b-instruct-2501",
"bleu": 0.315801608032821
},
{
"model": "google/gemini-2.0-flash-001",
"bleu": 0.3683733679689521
},
{
"model": "deepseek/deepseek-chat",
"bleu": 0.35988734604889566
},
{
"model": "microsoft/phi-4",
"bleu": 0.31289371159965956
}
],
"bleu": 0.3346024224541269
},
{
"language_name": "Japanese",
"language_code": "jpn",
"speakers": 128000000.0,
"scores": [
{
"model": "openai/gpt-4o-mini",
"bleu": 0.28991739992953497
},
{
"model": "meta-llama/llama-3.3-70b-instruct",
"bleu": 0.2675679907215641
},
{
"model": "mistralai/mistral-small-24b-instruct-2501",
"bleu": 0.21348802780641032
},
{
"model": "google/gemini-2.0-flash-001",
"bleu": 0.3345265427223546
},
{
"model": "deepseek/deepseek-chat",
"bleu": 0.3101203037558905
},
{
"model": "microsoft/phi-4",
"bleu": 0.2585222780278109
}
],
"bleu": 0.2790237571605942
},
{
"language_name": "Eastern Punjabi",
"language_code": "pan",
"speakers": 125000000.0,
"scores": [
{
"model": "meta-llama/llama-3.3-70b-instruct",
"bleu": 0.27325501919134315
}
],
"bleu": 0.27325501919134315
},
{
"language_name": "Standard German",
"language_code": "deu",
"speakers": 105000000.0,
"scores": [
{
"model": "openai/gpt-4o-mini",
"bleu": 0.39019323183176663
},
{
"model": "meta-llama/llama-3.3-70b-instruct",
"bleu": 0.37266353070949576
},
{
"model": "mistralai/mistral-small-24b-instruct-2501",
"bleu": 0.3647632576435612
},
{
"model": "google/gemini-2.0-flash-001",
"bleu": 0.4466723425292597
},
{
"model": "deepseek/deepseek-chat",
"bleu": 0.4045496243095387
},
{
"model": "microsoft/phi-4",
"bleu": 0.36047992103881465
}
],
"bleu": 0.3898869846770727
},
{
"language_name": "Egyptian Arabic",
"language_code": "arz",
"speakers": 100542400.0,
"scores": [
{
"model": "openai/gpt-4o-mini",
"bleu": 0.2339779422333898
},
{
"model": "meta-llama/llama-3.3-70b-instruct",
"bleu": 0.20475486619797384
},
{
"model": "mistralai/mistral-small-24b-instruct-2501",
"bleu": 0.20783660453505234
},
{
"model": "google/gemini-2.0-flash-001",
"bleu": 0.2840808045687292
},
{
"model": "deepseek/deepseek-chat",
"bleu": 0.2786287793608212
},
{
"model": "microsoft/phi-4",
"bleu": 0.19969813973959594
}
],
"bleu": 0.23482952277259375
},
{
"language_name": "Urdu",
"language_code": "urd",
"speakers": 94022900.0,
"scores": [
{
"model": "openai/gpt-4o-mini",
"bleu": 0.297325653414119
},
{
"model": "meta-llama/llama-3.3-70b-instruct",
"bleu": 0.24593966310665433
},
{
"model": "mistralai/mistral-small-24b-instruct-2501",
"bleu": 0.21988755291389567
},
{
"model": "google/gemini-2.0-flash-001",
"bleu": 0.31796430998058983
},
{
"model": "deepseek/deepseek-chat",
"bleu": 0.3043614136242901
},
{
"model": "microsoft/phi-4",
"bleu": 0.2285337340113323
}
],
"bleu": 0.2690020545084802
},
{
"language_name": "Filipino",
"language_code": "fil",
"speakers": 90000000.0,
"scores": [
{
"model": "meta-llama/llama-3.3-70b-instruct",
"bleu": 0.33268969497468076
}
],
"bleu": 0.33268969497468076
},
{
"language_name": "Javanese",
"language_code": "jav",
"speakers": 84308740.0,
"scores": [
{
"model": "meta-llama/llama-3.3-70b-instruct",
"bleu": 0.2528746866064681
}
],
"bleu": 0.2528746866064681
},
{
"language_name": "Marathi",
"language_code": "mar",
"speakers": 83100000.0,
"scores": [
{
"model": "meta-llama/llama-3.3-70b-instruct",
"bleu": 0.24876051941895777
}
],
"bleu": 0.24876051941895777
},
{
"language_name": "Swahili",
"language_code": "swh",
"speakers": 82300000.0,
"scores": [
{
"model": "openai/gpt-4o-mini",
"bleu": 0.34863560100932933
},
{
"model": "meta-llama/llama-3.3-70b-instruct",
"bleu": 0.30524292832054034
},
{
"model": "mistralai/mistral-small-24b-instruct-2501",
"bleu": 0.23580256234118713
},
{
"model": "google/gemini-2.0-flash-001",
"bleu": 0.3871437234807849
},
{
"model": "deepseek/deepseek-chat",
"bleu": 0.3476225063617937
},
{
"model": "microsoft/phi-4",
"bleu": 0.21803176063271826
}
],
"bleu": 0.3070798470243923
},
{
"language_name": "Turkish",
"language_code": "tur",
"speakers": 82231620.0,
"scores": [
{
"model": "meta-llama/llama-3.3-70b-instruct",
"bleu": 0.29874140544434125
}
],
"bleu": 0.29874140544434125
},
{
"language_name": "Telugu",
"language_code": "tel",
"speakers": 82000000.0,
"scores": [
{
"model": "meta-llama/llama-3.3-70b-instruct",
"bleu": 0.28869836899054496
}
],
"bleu": 0.28869836899054496
},
{
"language_name": "Wu Chinese",
"language_code": "wuu",
"speakers": 81400000.0,
"scores": [],
"bleu": null
},
{
"language_name": "Korean",
"language_code": "kor",
"speakers": 77300000.0,
"scores": [
{
"model": "meta-llama/llama-3.3-70b-instruct",
"bleu": 0.2566453806044083
}
],
"bleu": 0.2566453806044083
},
{
"language_name": "Vietnamese",
"language_code": "vie",
"speakers": 76000000.0,
"scores": [
{
"model": "openai/gpt-4o-mini",
"bleu": 0.3104431723374164
},
{
"model": "meta-llama/llama-3.3-70b-instruct",
"bleu": 0.3098478561790782
},
{
"model": "mistralai/mistral-small-24b-instruct-2501",
"bleu": 0.28074941515909896
},
{
"model": "google/gemini-2.0-flash-001",
"bleu": 0.37327273228460267
},
{
"model": "deepseek/deepseek-chat",
"bleu": 0.3487726531917602
},
{
"model": "microsoft/phi-4",
"bleu": 0.18355331419148843
}
],
"bleu": 0.3011065238905742
},
{
"language_name": "Tamil",
"language_code": "tam",
"speakers": 75000000.0,
"scores": [
{
"model": "openai/gpt-4o-mini",
"bleu": 0.24593649157372188
},
{
"model": "meta-llama/llama-3.3-70b-instruct",
"bleu": 0.24009996232522382
},
{
"model": "mistralai/mistral-small-24b-instruct-2501",
"bleu": 0.16785828803139252
},
{
"model": "google/gemini-2.0-flash-001",
"bleu": 0.3411457686951495
},
{
"model": "deepseek/deepseek-chat",
"bleu": 0.2875340171253509
},
{
"model": "microsoft/phi-4",
"bleu": 0.12646276530642359
}
],
"bleu": 0.23483954884287706
},
{
"language_name": "Yue Chinese",
"language_code": "yue",
"speakers": 73100000.0,
"scores": [
{
"model": "meta-llama/llama-3.3-70b-instruct",
"bleu": 0.2663995648378034
}
],
"bleu": 0.2663995648378034
},
{
"language_name": "Italian",
"language_code": "ita",
"speakers": 64819790.0,
"scores": [
{
"model": "meta-llama/llama-3.3-70b-instruct",
"bleu": 0.3190660116366235
}
],
"bleu": 0.3190660116366235
},
{
"language_name": "Gujarati",
"language_code": "guj",
"speakers": 56400000.0,
"scores": [
{
"model": "openai/gpt-4o-mini",
"bleu": 0.25754571533357745
},
{
"model": "meta-llama/llama-3.3-70b-instruct",
"bleu": 0.24145756515188838
},
{
"model": "mistralai/mistral-small-24b-instruct-2501",
"bleu": 0.20092063514315023
},
{
"model": "google/gemini-2.0-flash-001",
"bleu": 0.3664134239402827
},
{
"model": "deepseek/deepseek-chat",
"bleu": 0.2908883229704476
},
{
"model": "microsoft/phi-4",
"bleu": 0.19669824113063106
}
],
"bleu": 0.2589873172783296
},
{
"language_name": "Iranian Persian",
"language_code": "pes",
"speakers": 52800000.0,
"scores": [
{
"model": "meta-llama/llama-3.3-70b-instruct",
"bleu": 0.28359916806993934
}
],
"bleu": 0.28359916806993934
},
{
"language_name": "Bhojpuri",
"language_code": "bho",
"speakers": 52200000.0,
"scores": [
{
"model": "meta-llama/llama-3.3-70b-instruct",
"bleu": 0.24311504988281543
}
],
"bleu": 0.24311504988281543
},
{
"language_name": "Hakka Chinese",
"language_code": "hak",
"speakers": 48200000.0,
"scores": [],
"bleu": null
}
]