results/LLaMA-3-8B-Instruct.json

{"passkey": {"4k": 1.0, "8k": 1.0, "16k": 0, "32k": 0, "64k": 0, "128k": 0, "dataset_total_score": 0.3333333333333333}, "matreshka_yes_no": {"4k": 0.8394648829431438, "8k": 0.8, "16k": 0, "32k": 0, "64k": 0, "128k": 0, "dataset_total_score": 0.27324414715719064}, "matreshka_names": {"4k": 0.5333333333333333, "8k": 0.46, "16k": 0, "32k": 0, "64k": 0, "128k": 0, "dataset_total_score": 0.16555555555555557}, "passkey_with_librusec": {"4k": 1.0, "8k": 1.0, "16k": 0, "32k": 0, "64k": 0, "128k": 0, "dataset_total_score": 0.3333333333333333}, "librusec_history": {"8k": 0.90625, "16k": 0, "32k": 0, "64k": 0, "dataset_total_score": 0.2265625}, "ru_gsm100": {"16k": 0, "dataset_total_score": 0.0}, "ru_sci_passage_count": {"4k": 0.31, "8k": 0.08, "16k": 0, "32k": 0, "64k": 0, "128k": 0, "dataset_total_score": 0.065}, "ru_2wikimultihopqa": {"8k": 0.5306122448979592, "16k": 0, "32k": 0, "dataset_total_score": 0.17687074829931973}, "long_context_multiq": {"8k": 0.245, "4k": 0.05, "16k": 0, "32k": 0, "64k": 0, "128k": 0, "dataset_total_score": 0.049166666666666664}, "ru_sci_abstract_retrieval": {"4k": 0.9663095238095238, "8k": 0.9151886869744013, "16k": 0, "32k": 0, "64k": 0, "128k": 0, "dataset_total_score": 0.31358303513065416}, "ru_trec": {"4k": 0.5945945945945946, "8k": 0.5, "16k": 0, "32k": 0, "dataset_total_score": 0.2736486486486487}, "ru_sci_fi": {"32k": 0, "64k": 0, "dataset_total_score": 0.0}, "librusec_mhqa": {"8k": 0.4609375, "dataset_total_score": 0.4609375}, "ru_babilong_qa1": {"4k": 0.6862083333333334, "8k": 0.7335416666666665, "16k": 0, "32k": 0, "64k": 0, "128k": 0, "dataset_total_score": 0.236625}, "ru_babilong_qa2": {"4k": 0.14, "8k": 0.10866666666666668, "16k": 0, "32k": 0, "64k": 0, "128k": 0, "dataset_total_score": 0.04144444444444445}, "ru_babilong_qa3": {"4k": 0.09, "8k": 0.1798095238095238, "16k": 0, "32k": 0, "64k": 0, "128k": 0, "dataset_total_score": 0.04496825396825397}, "ru_babilong_qa4": {"4k": 0.5725714285714285, "8k": 0.6034285714285714, "16k": 0, "32k": 0, "64k": 0, "128k": 0, "dataset_total_score": 0.19599999999999998}, "ru_babilong_qa5": {"4k": 0.7666666666666667, "8k": 0.7516666666666667, "16k": 0, "32k": 0, "64k": 0, "128k": 0, "dataset_total_score": 0.2530555555555556}, "ru_quality": {"8k": 0.6910569105691058, "16k": 0, "dataset_total_score": 0.3455284552845529}, "ru_tpo": {"8k": 0.7808764940239044, "dataset_total_score": 0.7808764940239044}, "ru_qasper": {"8k": 0.06525418503550595, "16k": 0, "32k": 0, "dataset_total_score": 0.021751395011835317}, "total_score": 0.21864214601967852}