results/Mistral-7B-Instruct-v0.3.json

{"passkey": {"4k": 1.0, "8k": 1.0, "16k": 1.0, "32k": 1.0, "64k": 0, "128k": 0, "dataset_total_score": 0.6666666666666666}, "matreshka_yes_no": {"4k": 0.5652173913043478, "8k": 0.5066666666666667, "16k": 0.5466666666666666, "32k": 0.5, "64k": 0, "128k": 0, "dataset_total_score": 0.35309178743961356}, "matreshka_names": {"4k": 0.38, "8k": 0.32, "16k": 0.16666666666666666, "32k": 0.11333333333333333, "64k": 0, "128k": 0, "dataset_total_score": 0.1633333333333333}, "passkey_with_librusec": {"4k": 1.0, "8k": 1.0, "16k": 1.0, "32k": 0.995, "64k": 0, "128k": 0, "dataset_total_score": 0.6658333333333334}, "librusec_history": {"8k": 0.71875, "16k": 0.625, "32k": 0.6875, "64k": 0, "dataset_total_score": 0.5078125}, "ru_gsm100": {"16k": 0.11, "dataset_total_score": 0.11}, "ru_sci_passage_count": {"4k": 0.26, "8k": 0.14, "16k": 0.07, "32k": 0.02, "64k": 0, "128k": 0, "dataset_total_score": 0.08166666666666668}, "ru_2wikimultihopqa": {"8k": 0.5510204081632653, "16k": 0.46875, "32k": 0.2764227642276423, "dataset_total_score": 0.4320643907969692}, "long_context_multiq": {"8k": 0.22, "16k": 0.035, "4k": 0.035, "32k": 0.0, "64k": 0, "128k": 0, "dataset_total_score": 0.04833333333333334}, "ru_sci_abstract_retrieval": {"4k": 0.9824603174603175, "8k": 0.8690578865578865, "16k": 0.7111051699917106, "32k": 0.05148203921970241, "64k": 0, "128k": 0, "dataset_total_score": 0.43568423553826957}, "ru_trec": {"4k": 0.5675675675675675, "8k": 0.38, "16k": 0.4065934065934066, "32k": 0.3442622950819672, "dataset_total_score": 0.4246058173107353}, "ru_sci_fi": {"32k": 0.3055555555555556, "64k": 0, "dataset_total_score": 0.1527777777777778}, "librusec_mhqa": {"8k": 0.3359375, "dataset_total_score": 0.3359375}, "ru_babilong_qa1": {"4k": 0.25, "8k": 0.15, "16k": 0.22, "32k": 0.24, "64k": 0, "128k": 0, "dataset_total_score": 0.14333333333333334}, "ru_babilong_qa2": {"4k": 0.08, "8k": 0.05, "16k": 0.02, "32k": 0.02, "64k": 0, "128k": 0, "dataset_total_score": 0.028333333333333332}, "ru_babilong_qa3": {"4k": 0.1, "8k": 0.08, "16k": 0.1, "32k": 0.08, "64k": 0, "128k": 0, "dataset_total_score": 0.060000000000000005}, "ru_babilong_qa4": {"4k": 0.5178571428571428, "8k": 0.4428571428571429, "16k": 0.39285714285714285, "32k": 0.3028571428571429, "64k": 0, "128k": 0, "dataset_total_score": 0.2760714285714286}, "ru_babilong_qa5": {"4k": 0.5466666666666667, "8k": 0.62, "16k": 0.5533333333333333, "32k": 0.5333333333333333, "64k": 0, "128k": 0, "dataset_total_score": 0.3755555555555556}, "ru_quality": {"16k": 0.22981366459627334, "8k": 0.3821138211382114, "dataset_total_score": 0.30596374286724237}, "ru_tpo": {"8k": 0.6640106241699868, "dataset_total_score": 0.6640106241699868}, "ru_qasper": {"16k": 0.06576022201401649, "8k": 0.06619134922698901, "32k": 0.02936483912182809, "dataset_total_score": 0.05377213678761119}, "total_score": 0.2992784522292948}