cptu_bench / data.json
jansowa's picture
Add DeepSeek, Gemini Flash, Gemma 27B results
3c26d4f verified
raw
history blame
14.5 kB
[
{
"Model": "mistralai/Mistral-Large-Instruct-2407",
"Params": "123B",
"Average": 4.03025641025641,
"Sentiment": 4.230769230769231,
"Language understanding": 4.0,
"Phraseology": 3.86
},
{
"Model": "alpindale/WizardLM-2-8x22B",
"Params": "141B",
"Average": 3.9133760683760683,
"Sentiment": 3.7051282051282053,
"Language understanding": 3.815,
"Phraseology": 4.22
},
{
"Model": "meta-llama/Meta-Llama-3.1-70B-Instruct",
"Params": "70.6B",
"Average": 3.828974358974359,
"Sentiment": 4.326923076923077,
"Language understanding": 3.91,
"Phraseology": 3.25
},
{
"Model": "meta-llama/Meta-Llama-3-70B-Instruct",
"Params": "70.6B",
"Average": 3.806538461538462,
"Sentiment": 4.134615384615385,
"Language understanding": 3.82,
"Phraseology": 3.465
},
{
"Model": "speakleash/Bielik-11B-v2.3-Instruct",
"Params": "11.2B",
"Average": 3.7697863247863252,
"Sentiment": 3.9743589743589745,
"Language understanding": 3.785,
"Phraseology": 3.55
},
{
"Model": "mistralai/Mixtral-8x22B-Instruct-v0.1",
"Params": "141B",
"Average": 3.6690170940170943,
"Sentiment": 3.782051282051282,
"Language understanding": 3.675,
"Phraseology": 3.55
},
{
"Model": "speakleash/Bielik-11B-v2.1-Instruct",
"Params": "11.2B",
"Average": 3.6583760683760684,
"Sentiment": 3.9551282051282053,
"Language understanding": 3.915,
"Phraseology": 3.105
},
{
"Model": "Qwen/Qwen2-72B-Instruct",
"Params": "72.7B",
"Average": 3.6442735042735044,
"Sentiment": 3.7628205128205128,
"Language understanding": 3.89,
"Phraseology": 3.28
},
{
"Model": "speakleash/Bielik-11B-v2.0-Instruct",
"Params": "11.2B",
"Average": 3.614786324786325,
"Sentiment": 3.9743589743589745,
"Language understanding": 3.745,
"Phraseology": 3.125
},
{
"Model": "speakleash/Bielik-11B-v2.2-Instruct",
"Params": "11.2B",
"Average": 3.565982905982906,
"Sentiment": 3.717948717948718,
"Language understanding": 3.73,
"Phraseology": 3.25
},
{
"Model": "Qwen/Qwen1.5-72B-Chat",
"Params": "72.3B",
"Average": 3.3214529914529916,
"Sentiment": 3.4743589743589745,
"Language understanding": 3.515,
"Phraseology": 2.975
},
{
"Model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"Params": "8.03B",
"Average": 3.3114529914529918,
"Sentiment": 3.9743589743589745,
"Language understanding": 3.38,
"Phraseology": 2.58
},
{
"Model": "THUDM/glm-4-9b-chat",
"Params": "9.4B",
"Average": 3.2749145299145295,
"Sentiment": 3.58974358974359,
"Language understanding": 3.455,
"Phraseology": 2.78
},
{
"Model": "mistralai/Mistral-Nemo-Instruct-2407",
"Params": "12.2B",
"Average": 3.223675213675214,
"Sentiment": 3.641025641025641,
"Language understanding": 3.29,
"Phraseology": 2.74
},
{
"Model": "meta-llama/Meta-Llama-3-8B-Instruct",
"Params": "8.03B",
"Average": 3.172777777777778,
"Sentiment": 3.3333333333333335,
"Language understanding": 3.15,
"Phraseology": 3.035
},
{
"Model": "upstage/SOLAR-10.7B-Instruct-v1.0",
"Params": "10.7B",
"Average": 3.1343162393162394,
"Sentiment": 2.967948717948718,
"Language understanding": 3.18,
"Phraseology": 3.255
},
{
"Model": "speakleash/Bielik-7B-Instruct-v0.1",
"Params": "7.24B",
"Average": 3.126581196581197,
"Sentiment": 3.58974358974359,
"Language understanding": 3.475,
"Phraseology": 2.315
},
{
"Model": "openchat/openchat-3.5-0106-gemma",
"Params": "8.54B",
"Average": 3.08525641025641,
"Sentiment": 3.730769230769231,
"Language understanding": 3.08,
"Phraseology": 2.445
},
{
"Model": "mistralai/Mixtral-8x7B-Instruct-v0.1",
"Params": "46.7B",
"Average": 3.039230769230769,
"Sentiment": 3.0576923076923075,
"Language understanding": 3.175,
"Phraseology": 2.885
},
{
"Model": "mistralai/Mistral-7B-Instruct-v0.3",
"Params": "7.25B",
"Average": 3.022307692307692,
"Sentiment": 3.326923076923077,
"Language understanding": 3.06,
"Phraseology": 2.68
},
{
"Model": "berkeley-nest/Starling-LM-7B-alpha",
"Params": "7.24B",
"Average": 2.945897435897436,
"Sentiment": 3.0576923076923075,
"Language understanding": 2.925,
"Phraseology": 2.855
},
{
"Model": "openchat/openchat-3.5-0106",
"Params": "7.24B",
"Average": 2.8500854700854696,
"Sentiment": 3.16025641025641,
"Language understanding": 2.835,
"Phraseology": 2.555
},
{
"Model": "internlm/internlm2-chat-20b",
"Params": "19.9B",
"Average": 2.8237606837606837,
"Sentiment": 3.301282051282051,
"Language understanding": 2.785,
"Phraseology": 2.385
},
{
"Model": "01-ai/Yi-1.5-34B-Chat",
"Params": "34.4B",
"Average": 2.7756410256410255,
"Sentiment": 3.076923076923077,
"Language understanding": 2.87,
"Phraseology": 2.38
},
{
"Model": "Voicelab/trurl-2-13b-academic",
"Params": "13B",
"Average": 2.74042735042735,
"Sentiment": 3.301282051282051,
"Language understanding": 2.755,
"Phraseology": 2.165
},
{
"Model": "google/gemma-2-2b-it",
"Params": "2.61B",
"Average": 2.7974786324786325,
"Sentiment": 3.3974358974359,
"Language understanding": 2.9,
"Phraseology": 2.095
},
{
"Model": "Qwen/Qwen2.5-3B-Instruct",
"Params": "3.09B",
"Average": 2.734572649572649,
"Sentiment": 2.948717948717949,
"Language understanding": 2.455,
"Phraseology": 2.8
},
{
"Model": "NousResearch/Hermes-3-Llama-3.2-3B",
"Params": "3.21B",
"Average": 2.695128205128205,
"Sentiment": 2.6153846153846154,
"Language understanding": 2.705,
"Phraseology": 2.765
},
{
"Model": "ibm-granite/granite-3.1-2b-instruct",
"Params": "2.53B",
"Average": 2.397307692307692,
"Sentiment": 3.076923076923077,
"Language understanding": 2.235,
"Phraseology": 1.88
},
{
"Model": "meta-llama/Llama-3.2-1B-Instruct",
"Params": "1.24B",
"Average": 2.383974358974359,
"Sentiment": 3.076923076923077,
"Language understanding": 1.735,
"Phraseology": 2.34
},
{
"Model": "microsoft/Phi-3.5-mini-instruct",
"Params": "3.82B",
"Average": 2.331965811965812,
"Sentiment": 2.435897435897436,
"Language understanding": 2.135,
"Phraseology": 2.425
},
{
"Model": "meta-llama/Llama-3.2-3B-Instruct",
"Params": "3.21B",
"Average": 2.257136752136752,
"Sentiment": 2.7564102564102564,
"Language understanding": 2.295,
"Phraseology": 1.72
},
{
"Model": "h2oai/h2o-danube2-1.8b-chat",
"Params": "1.83B",
"Average": 2.1455982905982904,
"Sentiment": 2.371794871794872,
"Language understanding": 1.595,
"Phraseology": 2.47
},
{
"Model": "Qwen/Qwen2.5-1.5B-Instruct",
"Params": "1.54B",
"Average": 2.1232905982905983,
"Sentiment": 2.7948717948717947,
"Language understanding": 1.35,
"Phraseology": 2.225
},
{
"Model": "utter-project/EuroLLM-1.7B-Instruct",
"Params": "1.66B",
"Average": 2.097863247863248,
"Sentiment": 2.243589743589744,
"Language understanding": 1.79,
"Phraseology": 2.26
},
{
"Model": "LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct",
"Params": "2.41B",
"Average": 2.062846282695529,
"Sentiment": 1.9423076923076923,
"Language understanding": 2.1155778894472363,
"Phraseology": 2.130653266331658
},
{
"Model": "HuggingFaceTB/SmolLM2-1.7B-Instruct",
"Params": "1.71B",
"Average": 1.9102136752136751,
"Sentiment": 2.275641025641025,
"Language understanding": 1.1,
"Phraseology": 2.355
},
{
"Model": "Qwen/Qwen2.5-0.5B-Instruct",
"Params": "0.49B",
"Average": 1.7950427350427354,
"Sentiment": 1.955128205128205,
"Language understanding": 0.835,
"Phraseology": 2.595
},
{
"Model": "CYFRAGOVPL/Llama-PLLuM-70B-chat",
"Params": "70.6B",
"Average": 3.63,
"Sentiment": 3.94,
"Language understanding": 3.61,
"Phraseology": 3.35
},
{
"Model": "CYFRAGOVPL/PLLuM-8x7B-nc-instruct",
"Params": "46.7B",
"Average": 3.56,
"Sentiment": 3.88,
"Language understanding": 3.59,
"Phraseology": 3.22
},
{
"Model": "CYFRAGOVPL/Llama-PLLuM-70B-instruct",
"Params": "70.6B",
"Average": 3.56,
"Sentiment": 3.78,
"Language understanding": 3.63,
"Phraseology": 3.26
},
{
"Model": "CYFRAGOVPL/PLLuM-8x7B-instruct",
"Params": "46.7B",
"Average": 3.50,
"Sentiment": 3.59,
"Language understanding": 3.47,
"Phraseology": 3.46
},
{
"Model": "CYFRAGOVPL/PLLuM-12B-instruct",
"Params": "12.2B",
"Average": 3.49,
"Sentiment": 3.71,
"Language understanding": 3.17,
"Phraseology": 3.59
},
{
"Model": "CYFRAGOVPL/PLLuM-8x7B-nc-chat",
"Params": "46.7B",
"Average": 3.44,
"Sentiment": 3.76,
"Language understanding": 3.48,
"Phraseology": 3.08
},
{
"Model": "CYFRAGOVPL/PLLuM-8x7B-chat",
"Params": "46.7B",
"Average": 3.41,
"Sentiment": 3.44,
"Language understanding": 3.45,
"Phraseology": 3.35
},
{
"Model": "CYFRAGOVPL/PLLuM-12B-chat",
"Params": "12.2B",
"Average": 3.32,
"Sentiment": 3.32,
"Language understanding": 3.21,
"Phraseology": 3.43
},
{
"Model": "CYFRAGOVPL/PLLuM-12B-nc-instruct",
"Params": "12.2B",
"Average": 3.29,
"Sentiment": 3.24,
"Language understanding": 3.31,
"Phraseology": 3.32
},
{
"Model": "CYFRAGOVPL/Llama-PLLuM-8B-instruct",
"Params": "8.03B",
"Average": 3.20,
"Sentiment": 3.24,
"Language understanding": 2.90,
"Phraseology": 3.46
},
{
"Model": "CYFRAGOVPL/Llama-PLLuM-8B-chat",
"Params": "8.03B",
"Average": 3.14,
"Sentiment": 3.13,
"Language understanding": 2.93,
"Phraseology": 3.36
},
{
"Model": "CYFRAGOVPL/PLLuM-12B-nc-chat",
"Params": "12.2B",
"Average": 3.33,
"Sentiment": 3.22,
"Language understanding": 3.23,
"Phraseology": 3.54
},
{
"Model": "Qwen/Qwen2.5-72B-Instruct",
"Params": "72.7B",
"Average": 3.9923076923076923,
"Sentiment": 4.076923076923077,
"Language understanding": 3.97,
"Phraseology": 3.93
},
{
"Model": "Qwen/Qwen2.5-32B-Instruct",
"Params": "32.8B",
"Average": 3.8047008547008545,
"Sentiment": 3.8141025641025643,
"Language understanding": 3.565,
"Phraseology": 4.035
},
{
"Model": "mistralai/Mistral-Small-24B-Instruct-2501",
"Params": "23.6B",
"Average": 3.79508547008547,
"Sentiment": 3.91025641025641,
"Language understanding": 3.6,
"Phraseology": 3.875
},
{
"Model": "meta-llama/Llama-3.3-70B-Instruct",
"Params": "70.6B",
"Average": 3.7332905982905977,
"Sentiment": 4.294871794871795,
"Language understanding": 3.865,
"Phraseology": 3.04
},
{
"Model": "Qwen/Qwen2.5-14B-Instruct",
"Params": "14.8B",
"Average": 3.61508547008547,
"Sentiment": 3.91025641025641,
"Language understanding": 3.565,
"Phraseology": 3.37
},
{
"Model": "microsoft/phi-4",
"Params": "14.7B",
"Average": 3.4976495726495727,
"Sentiment": 3.717948717948718,
"Language understanding": 3.54,
"Phraseology": 3.235
},
{
"Model": "Qwen/Qwen2.5-7B-Instruct",
"Params": "7.62B",
"Average": 3.2258974358974357,
"Sentiment": 3.5576923076923075,
"Language understanding": 3.025,
"Phraseology": 3.095
},
{
"Model": "microsoft/Phi-4-mini-instruct",
"Params": "3.84B",
"Average": 2.455769230769231,
"Sentiment": 2.6923076923076925,
"Language understanding": 2.43,
"Phraseology": 2.245
},
{
"Model": "gemini-2.0-flash-001",
"Params": "",
"Average": 4.393076923076923,
"Sentiment": 4.519230769230769,
"Language understanding": 4.32,
"Phraseology": 4.34
},
{
"Model": "gemini-2.0-flash-lite-001",
"Params": "",
"Average": 4.173589743589743,
"Sentiment": 4.230769230769231,
"Language understanding": 4.055,
"Phraseology": 4.235
},
{
"Model": "deepseek-ai/DeepSeek-V3 (API)",
"Params": "685B",
"Average": 4.034658119658119,
"Sentiment": 4.358974358974359,
"Language understanding": 4.22,
"Phraseology": 3.525
},
{
"Model": "google/gemma-3-27b-it (API)",
"Params": "27.4B",
"Average": 3.896068376068376,
"Sentiment": 3.878205128205128,
"Language understanding": 3.785,
"Phraseology": 4.025
}
]