results/Mistral-Nemo-Instruct-2407.json

{"passkey": {"4k": 1.0, "8k": 1.0, "16k": 1.0, "32k": 1.0, "64k": 1.0, "128k": 0.87, "dataset_total_score": 0.9783333333333334}, "matreshka_yes_no": {"4k": 0.6555183946488294, "8k": 0.5366666666666666, "16k": 0.5, "32k": 0.5, "64k": 0.5, "128k": 0.5, "dataset_total_score": 0.5320308435525827}, "matreshka_names": {"4k": 0.6133333333333333, "8k": 0.5, "16k": 0.43333333333333335, "32k": 0.29333333333333333, "64k": 0.07333333333333333, "128k": 0.02, "dataset_total_score": 0.3222222222222222}, "passkey_with_librusec": {"4k": 1.0, "8k": 1.0, "16k": 1.0, "32k": 0.995, "64k": 1.0, "128k": 0.97, "dataset_total_score": 0.9941666666666666}, "librusec_history": {"8k": 0.59375, "16k": 0.5625, "32k": 0.5, "64k": 0.46875, "dataset_total_score": 0.53125}, "ru_gsm100": {"16k": 0.0, "dataset_total_score": 0.0}, "ru_sci_passage_count": {"4k": 0.57, "8k": 0.1, "16k": 0.05, "32k": 0.03, "64k": 0.0, "128k": 0.02, "dataset_total_score": 0.12833333333333333}, "ru_2wikimultihopqa": {"8k": 0.3469387755102041, "16k": 0.3125, "32k": 0.17886178861788618, "dataset_total_score": 0.27943352137603006}, "long_context_multiq": {"8k": 0.23, "16k": 0.025, "4k": 0.05, "64k": 0.005, "32k": 0.0, "128k": 0.0, "dataset_total_score": 0.05166666666666667}, "ru_sci_abstract_retrieval": {"4k": 0.9843253968253969, "8k": 0.9340110286538859, "16k": 0.882861713382518, "32k": 0.7548755510867896, "64k": 0.28580245595851705, "128k": 0.07901305389621614, "dataset_total_score": 0.6534815333005539}, "ru_trec": {"4k": 0.4864864864864865, "8k": 0.66, "16k": 0.7142857142857143, "32k": 0.47540983606557374, "dataset_total_score": 0.5840455092094436}, "ru_sci_fi": {"32k": 0.2222222222222222, "64k": 0.25, "dataset_total_score": 0.2361111111111111}, "librusec_mhqa": {"8k": 0.2994791666666667, "dataset_total_score": 0.2994791666666667}, "ru_babilong_qa1": {"4k": 0.71, "8k": 0.73, "16k": 0.59, "32k": 0.6, "64k": 0.46, "128k": 0.19, "dataset_total_score": 0.5466666666666666}, "ru_babilong_qa2": {"4k": 0.28, "8k": 0.26, "16k": 0.19, "32k": 0.16, "64k": 0.11, "128k": 0.04, "dataset_total_score": 0.17333333333333334}, "ru_babilong_qa3": {"4k": 0.22, "8k": 0.28, "16k": 0.14, "32k": 0.14, "64k": 0.11, "128k": 0.07, "dataset_total_score": 0.16}, "ru_babilong_qa4": {"4k": 0.16928571428571432, "8k": 0.18714285714285717, "16k": 0.20142857142857143, "32k": 0.1635714285714286, "64k": 0.02, "128k": 0.0, "dataset_total_score": 0.1235714285714286}, "ru_babilong_qa5": {"4k": 0.48, "8k": 0.5, "16k": 0.49, "32k": 0.4566666666666667, "64k": 0.43, "128k": 0.3966666666666667, "dataset_total_score": 0.45888888888888896}, "ru_quality": {"16k": 0.6811594202898551, "8k": 0.6585365853658537, "dataset_total_score": 0.6698480028278544}, "ru_tpo": {"8k": 0.7675962815405047, "dataset_total_score": 0.7675962815405047}, "ru_qasper": {"16k": 0.28639727595549347, "8k": 0.3018572041274937, "32k": 0.14594086192630237, "dataset_total_score": 0.2447317806697632}, "total_score": 0.41596144237795474}