Polish_Medical_Exams / leaderboards /ldek_en_accs.json
michal
Upload
3930665
raw
history blame
10.5 kB
[
{
"model_name": "model-meta-llama-Llama-3.1-8B-Instruct",
"2022 Spring": 49.494949494949495,
"2014 Spring": 42.857142857142854,
"2022 Fall": 45.91836734693878,
"2014 Fall": 46.1139896373057,
"2024 Spring": 47.20812182741117,
"2015 Spring": 54.3010752688172,
"2023 Spring": 46.96969696969697,
"2021 Fall": 48.98989898989899,
"2015 Fall": 47.89473684210526,
"2023 Fall": 49.743589743589745,
"2021 Spring": 46.93877551020408,
"2013 Spring": 47.42268041237113,
"2013 Fall": 46.596858638743456,
"overall_accuracy": 47.70569620253164
},
{
"model_name": "model-BioMistral-BioMistral-7B",
"2022 Spring": 22.727272727272727,
"2014 Spring": 20.408163265306122,
"2022 Fall": 32.6530612244898,
"2014 Fall": 22.279792746113987,
"2024 Spring": 29.949238578680205,
"2015 Spring": 25.806451612903224,
"2023 Spring": 27.77777777777778,
"2021 Fall": 29.292929292929294,
"2015 Fall": 29.47368421052631,
"2023 Fall": 27.692307692307693,
"2021 Spring": 22.448979591836736,
"2013 Spring": 28.865979381443296,
"2013 Fall": 28.79581151832461,
"overall_accuracy": 26.78006329113924
},
{
"model_name": "model-johnsnowlabs-JSL-MedLlama-3-8B-v2.0",
"2022 Spring": 38.88888888888889,
"2014 Spring": 34.69387755102041,
"2022 Fall": 40.30612244897959,
"2014 Fall": 37.82383419689119,
"2024 Spring": 41.62436548223351,
"2015 Spring": 40.32258064516129,
"2023 Spring": 36.868686868686865,
"2021 Fall": 44.94949494949495,
"2015 Fall": 35.26315789473684,
"2023 Fall": 37.43589743589744,
"2021 Spring": 40.816326530612244,
"2013 Spring": 41.23711340206185,
"2013 Fall": 42.40837696335078,
"overall_accuracy": 39.438291139240505
},
{
"model_name": "model-Qwen-Qwen2.5-7B-Instruct",
"2022 Spring": 46.464646464646464,
"2014 Spring": 46.42857142857143,
"2022 Fall": 46.93877551020408,
"2014 Fall": 49.740932642487046,
"2024 Spring": 53.299492385786806,
"2015 Spring": 44.086021505376344,
"2023 Spring": 48.98989898989899,
"2021 Fall": 53.03030303030303,
"2015 Fall": 44.21052631578947,
"2023 Fall": 47.179487179487175,
"2021 Spring": 51.53061224489795,
"2013 Spring": 52.0618556701031,
"2013 Fall": 44.50261780104712,
"overall_accuracy": 48.37816455696203
},
{
"model_name": "model-speakleash-Bielik-11B-v2.2-Instruct",
"2022 Spring": 39.8989898989899,
"2014 Spring": 36.734693877551024,
"2022 Fall": 38.265306122448976,
"2014 Fall": 44.04145077720207,
"2024 Spring": 50.25380710659898,
"2015 Spring": 39.247311827956985,
"2023 Spring": 38.88888888888889,
"2021 Fall": 42.92929292929293,
"2015 Fall": 42.10526315789473,
"2023 Fall": 43.58974358974359,
"2021 Spring": 48.97959183673469,
"2013 Spring": 49.48453608247423,
"2013 Fall": 42.93193717277487,
"overall_accuracy": 42.879746835443036
},
{
"model_name": "model-gpt-4o-2024-08-06",
"2022 Spring": 74.74747474747475,
"2014 Spring": 72.44897959183673,
"2022 Fall": 71.42857142857143,
"2014 Fall": 74.09326424870466,
"2024 Spring": 73.09644670050761,
"2015 Spring": 66.66666666666666,
"2023 Spring": 71.21212121212122,
"2021 Fall": 74.74747474747475,
"2015 Fall": 71.05263157894737,
"2023 Fall": 70.76923076923077,
"2021 Spring": 77.55102040816327,
"2013 Spring": 72.68041237113401,
"2013 Fall": 71.72774869109948,
"overall_accuracy": 72.50791139240506
},
{
"model_name": "model-OpenMeditron-Meditron3-8B",
"2022 Spring": 42.92929292929293,
"2014 Spring": 38.775510204081634,
"2022 Fall": 44.38775510204081,
"2014 Fall": 44.04145077720207,
"2024 Spring": 40.10152284263959,
"2015 Spring": 45.16129032258064,
"2023 Spring": 41.91919191919192,
"2021 Fall": 44.94949494949495,
"2015 Fall": 42.10526315789473,
"2023 Fall": 41.53846153846154,
"2021 Spring": 43.36734693877551,
"2013 Spring": 46.90721649484536,
"2013 Fall": 47.64397905759162,
"overall_accuracy": 43.35443037974683
},
{
"model_name": "model-gpt-4o-mini-2024-07-18",
"2022 Spring": 54.54545454545454,
"2014 Spring": 55.61224489795919,
"2022 Fall": 56.12244897959183,
"2014 Fall": 56.994818652849744,
"2024 Spring": 56.34517766497462,
"2015 Spring": 56.98924731182796,
"2023 Spring": 56.060606060606055,
"2021 Fall": 55.55555555555556,
"2015 Fall": 54.21052631578947,
"2023 Fall": 58.97435897435898,
"2021 Spring": 62.755102040816325,
"2013 Spring": 58.24742268041238,
"2013 Fall": 57.06806282722513,
"overall_accuracy": 56.88291139240506
},
{
"model_name": "model-OpenMeditron-Meditron3-70B",
"2022 Spring": 43.93939393939394,
"2014 Spring": 40.30612244897959,
"2022 Fall": 47.95918367346938,
"2014 Fall": 45.07772020725388,
"2024 Spring": 49.23857868020304,
"2015 Spring": 45.16129032258064,
"2023 Spring": 43.43434343434344,
"2021 Fall": 48.98989898989899,
"2015 Fall": 48.94736842105264,
"2023 Fall": 45.64102564102564,
"2021 Spring": 46.42857142857143,
"2013 Spring": 46.391752577319586,
"2013 Fall": 46.07329842931937,
"overall_accuracy": 45.96518987341772
},
{
"model_name": "model-aaditya-Llama3-OpenBioLLM-70B",
"2022 Spring": 44.44444444444444,
"2014 Spring": 45.40816326530612,
"2022 Fall": 46.93877551020408,
"2014 Fall": 47.15025906735752,
"2024 Spring": 48.223350253807105,
"2015 Spring": 45.16129032258064,
"2023 Spring": 45.95959595959596,
"2021 Fall": 48.484848484848484,
"2015 Fall": 46.31578947368421,
"2023 Fall": 41.02564102564102,
"2021 Spring": 45.91836734693878,
"2013 Spring": 46.391752577319586,
"2013 Fall": 45.0261780104712,
"overall_accuracy": 45.88607594936709
},
{
"model_name": "model-meta-llama-Llama-3.2-3B-Instruct",
"2022 Spring": 34.34343434343434,
"2014 Spring": 32.6530612244898,
"2022 Fall": 39.285714285714285,
"2014 Fall": 35.751295336787564,
"2024 Spring": 39.59390862944163,
"2015 Spring": 38.70967741935484,
"2023 Spring": 39.39393939393939,
"2021 Fall": 37.878787878787875,
"2015 Fall": 35.78947368421053,
"2023 Fall": 37.43589743589744,
"2021 Spring": 37.755102040816325,
"2013 Spring": 33.50515463917525,
"2013 Fall": 37.17277486910995,
"overall_accuracy": 36.86708860759494
},
{
"model_name": "model-mistralai-Mistral-Large-Instruct-2407",
"2022 Spring": 61.61616161616161,
"2014 Spring": 61.73469387755102,
"2022 Fall": 60.204081632653065,
"2014 Fall": 63.212435233160626,
"2024 Spring": 64.9746192893401,
"2015 Spring": 62.365591397849464,
"2023 Spring": 60.60606060606061,
"2021 Fall": 62.62626262626263,
"2015 Fall": 61.578947368421055,
"2023 Fall": 59.48717948717949,
"2021 Spring": 64.28571428571429,
"2013 Spring": 63.91752577319587,
"2013 Fall": 61.25654450261781,
"overall_accuracy": 62.14398734177215
},
{
"model_name": "model-meta-llama-Meta-Llama-3.1-70B-Instruct",
"2022 Spring": 65.15151515151516,
"2014 Spring": 62.755102040816325,
"2022 Fall": 62.244897959183675,
"2014 Fall": 64.24870466321244,
"2024 Spring": 59.89847715736041,
"2015 Spring": 68.27956989247312,
"2023 Spring": 64.64646464646465,
"2021 Fall": 62.121212121212125,
"2015 Fall": 63.1578947368421,
"2023 Fall": 56.92307692307692,
"2021 Spring": 67.85714285714286,
"2013 Spring": 61.34020618556701,
"2013 Fall": 62.82722513089005,
"overall_accuracy": 63.17246835443038
},
{
"model_name": "model-ProbeMedicalYonseiMAILab-medllama3-v20",
"2022 Spring": 36.868686868686865,
"2014 Spring": 34.69387755102041,
"2022 Fall": 37.755102040816325,
"2014 Fall": 35.751295336787564,
"2024 Spring": 43.14720812182741,
"2015 Spring": 43.54838709677419,
"2023 Spring": 39.8989898989899,
"2021 Fall": 35.35353535353536,
"2015 Fall": 37.89473684210527,
"2023 Fall": 34.87179487179487,
"2021 Spring": 38.775510204081634,
"2013 Spring": 41.75257731958763,
"2013 Fall": 39.79057591623037,
"overall_accuracy": 38.449367088607595
},
{
"model_name": "model-mistralai-Mistral-Small-Instruct-2409",
"2022 Spring": 37.878787878787875,
"2014 Spring": 45.91836734693878,
"2022 Fall": 45.91836734693878,
"2014 Fall": 43.005181347150256,
"2024 Spring": 45.68527918781726,
"2015 Spring": 44.623655913978496,
"2023 Spring": 40.909090909090914,
"2021 Fall": 40.4040404040404,
"2015 Fall": 44.21052631578947,
"2023 Fall": 42.05128205128205,
"2021 Spring": 46.42857142857143,
"2013 Spring": 44.329896907216494,
"2013 Fall": 43.97905759162304,
"overall_accuracy": 43.473101265822784
},
{
"model_name": "model-Qwen-Qwen2.5-72B-Instruct",
"2022 Spring": 65.15151515151516,
"2014 Spring": 61.73469387755102,
"2022 Fall": 64.79591836734694,
"2014 Fall": 66.32124352331607,
"2024 Spring": 63.45177664974619,
"2015 Spring": 62.365591397849464,
"2023 Spring": 59.09090909090909,
"2021 Fall": 65.15151515151516,
"2015 Fall": 63.1578947368421,
"2023 Fall": 58.46153846153847,
"2021 Spring": 69.38775510204081,
"2013 Spring": 64.94845360824742,
"2013 Fall": 59.16230366492147,
"overall_accuracy": 63.33069620253164
}
]