Files
LMCocktail-10.7B-v1/alpaca_eval/chatgpt_fn_--SOLAR-10-7B-LMCocktail/leaderboard.csv
ModelHub XC 512cc0315f 初始化项目,由ModelHub XC社区提供模型
Model: Yhyu13/LMCocktail-10.7B-v1
Source: Original Platform
2026-05-07 15:59:14 +08:00

1.1 KiB

1win_ratestandard_errorn_winsn_wins_basen_drawsn_totalmodeavg_length
2gpt473.78881987577641.535980154507359758820512805minimal1365
3SOLAR-10.7B-LMCocktail73.445273631840791.55721503636433985902131804community1203
4claude70.372670807453421.5995195071478285622349805minimal1082
5chatgpt66.086956521739131.66264799943303175292706805minimal811
6wizardlm-13b65.155279503105591.6700341077875655202769805minimal985
7vicuna-13b64.099378881987581.68951858631531465152882805minimal1037
8guanaco-65b62.360248447204971.70863488116057655023030805minimal1249
9oasst-rlhf-llama-33b62.04968944099381.70800289761035144983043805minimal1079
10alpaca-farm-ppo-human60.248447204968951.71694967335487724813168805minimal803
11falcon-40b-instruct56.521739130434781.74387505203129444533484805minimal662
12phi-2-alpaca-gpt4-dpo55.597014925373131.75337192453849894473570804community4532
13text_davinci_00350.00.000805805minimal307
14alpaca-7b45.217391304347831.737584678157947635643316805minimal396
15text_davinci_00128.074534161490681.560218342658748421656920805minimal296