Files
ai-agent-book/chapter7/elo-leaderboard/validation/runs/exp7-7-arena-20260731-v1/bradley_terry.json
T
liqiang b119135836
Build latest book artifacts / build (push) Canceled after 0s
dependency resolution / resolve (3.11) (push) Canceled after 0s
dependency resolution / resolve (3.13) (push) Canceled after 0s
deploy-pages / build (push) Canceled after 0s
deploy-pages / deploy (push) Canceled after 0s
i18n consistency check / check (push) Canceled after 0s
provider adoption tests / test (chapter2/context-compression) (push) Canceled after 0s
provider adoption tests / test (chapter2/prompt-injection) (push) Canceled after 0s
provider adoption tests / test (chapter2/system-hint) (push) Canceled after 0s
provider adoption tests / test (chapter3/log-sanitization) (push) Canceled after 0s
web-search-agent tests / test (push) Canceled after 0s
web-search-agent tests / agentbook (push) Canceled after 0s
ai-agent-book 精选快照(<2MB 代码与文档,来自 github.com/bojieli/ai-agent-book)
2026-08-20 13:12:50 +00:00

906 lines
19 KiB
JSON

[
{
"lower_ci": 1199.4356201692,
"model": "chatgpt-4o-latest",
"rank": 1,
"rating": 1202.8722324768,
"upper_ci": 1207.3805726125
},
{
"lower_ci": 1182.767114327,
"model": "gemini-1.5-pro-exp-0801",
"rank": 2,
"rating": 1187.3727762743,
"upper_ci": 1191.7564879767
},
{
"lower_ci": 1173.1270556478,
"model": "gpt-4o-2024-05-13",
"rank": 3,
"rating": 1174.5475812185,
"upper_ci": 1177.0403252386
},
{
"lower_ci": 1161.1978031325,
"model": "gpt-4o-mini-2024-07-18",
"rank": 4,
"rating": 1162.9712796813,
"upper_ci": 1166.568334134
},
{
"lower_ci": 1156.0224735749,
"model": "claude-3-5-sonnet-20240620",
"rank": 5,
"rating": 1159.6692177384,
"upper_ci": 1161.8458744744
},
{
"lower_ci": 1153.6447817793,
"model": "gemini-advanced-0514",
"rank": 6,
"rating": 1155.6305094344,
"upper_ci": 1157.1030226933
},
{
"lower_ci": 1150.4614200682,
"model": "llama-3.1-405b-instruct",
"rank": 7,
"rating": 1153.3950109278,
"upper_ci": 1157.0848375454
},
{
"lower_ci": 1146.348878889,
"model": "gpt-4o-2024-08-06",
"rank": 8,
"rating": 1150.7428051987,
"upper_ci": 1156.3245456986
},
{
"lower_ci": 1146.7772301944,
"model": "gemini-1.5-pro-api-0514",
"rank": 9,
"rating": 1149.1265569601,
"upper_ci": 1151.5010539806
},
{
"lower_ci": 1143.6682527667,
"model": "gemini-1.5-pro-api-0409-preview",
"rank": 10,
"rating": 1146.1756037638,
"upper_ci": 1147.8895040945
},
{
"lower_ci": 1142.3990049162,
"model": "gpt-4-turbo-2024-04-09",
"rank": 11,
"rating": 1144.9187340632,
"upper_ci": 1146.8362809167
},
{
"lower_ci": 1138.1303324947,
"model": "gpt-4-1106-preview",
"rank": 12,
"rating": 1139.5004505155,
"upper_ci": 1140.97644635
},
{
"lower_ci": 1136.3852091186,
"model": "mistral-large-2407",
"rank": 13,
"rating": 1139.3566231011,
"upper_ci": 1143.8960727747
},
{
"lower_ci": 1135.0624903381,
"model": "athene-70b-0725",
"rank": 14,
"rating": 1138.2016223593,
"upper_ci": 1141.397916447
},
{
"lower_ci": 1135.0278139027,
"model": "claude-3-opus-20240229",
"rank": 15,
"rating": 1136.5739464324,
"upper_ci": 1137.5663039742
},
{
"lower_ci": 1131.7219814044,
"model": "llama-3.1-70b-instruct",
"rank": 16,
"rating": 1134.8942150397,
"upper_ci": 1139.3028524197
},
{
"lower_ci": 1132.1800230236,
"model": "gpt-4-0125-preview",
"rank": 17,
"rating": 1133.974390087,
"upper_ci": 1135.7552442263
},
{
"lower_ci": 1127.3300289872,
"model": "yi-large-preview",
"rank": 18,
"rating": 1128.1692229165,
"upper_ci": 1131.371743138
},
{
"lower_ci": 1111.850158929,
"model": "reka-core-20240722",
"rank": 19,
"rating": 1117.1464671073,
"upper_ci": 1121.9537941313
},
{
"lower_ci": 1114.0244965884,
"model": "gemini-1.5-flash-api-0514",
"rank": 20,
"rating": 1116.6161359294,
"upper_ci": 1118.5223962538
},
{
"lower_ci": 1103.6704090106,
"model": "deepseek-v2-api-0628",
"rank": 21,
"rating": 1107.2808888587,
"upper_ci": 1112.0417779712
},
{
"lower_ci": 1103.9432951297,
"model": "gemma-2-27b-it",
"rank": 22,
"rating": 1105.9132519337,
"upper_ci": 1108.0293102426
},
{
"lower_ci": 1099.3459906048,
"model": "deepseek-coder-v2-0724",
"rank": 23,
"rating": 1105.3954927337,
"upper_ci": 1113.0353361228
},
{
"lower_ci": 1099.9821845459,
"model": "yi-large",
"rank": 24,
"rating": 1102.4018397329,
"upper_ci": 1104.8525831946
},
{
"lower_ci": 1094.5198632757,
"model": "nemotron-4-340b-instruct",
"rank": 25,
"rating": 1098.0765768899,
"upper_ci": 1100.3082488796
},
{
"lower_ci": 1092.3225621341,
"model": "bard-jan-24-gemini-pro",
"rank": 26,
"rating": 1096.589845604,
"upper_ci": 1104.5333605578
},
{
"lower_ci": 1089.9500461084,
"model": "glm-4-0520",
"rank": 27,
"rating": 1095.5341569364,
"upper_ci": 1100.1005750187
},
{
"lower_ci": 1093.6731280724,
"model": "llama-3-70b-instruct",
"rank": 28,
"rating": 1094.9281802329,
"upper_ci": 1095.7283536945
},
{
"lower_ci": 1088.0897564085,
"model": "claude-3-sonnet-20240229",
"rank": 29,
"rating": 1090.1434308802,
"upper_ci": 1091.5131310821
},
{
"lower_ci": 1086.224736458,
"model": "reka-core-20240501",
"rank": 30,
"rating": 1088.4321613308,
"upper_ci": 1090.272779249
},
{
"lower_ci": 1082.4844014079,
"model": "reka-flash-20240722",
"rank": 31,
"rating": 1088.2114217704,
"upper_ci": 1094.1409244278
},
{
"lower_ci": 1076.2505646464,
"model": "command-r-plus",
"rank": 32,
"rating": 1078.6392855764,
"upper_ci": 1080.5241685262
},
{
"lower_ci": 1072.978332193,
"model": "gemma-2-9b-it",
"rank": 33,
"rating": 1076.1200490762,
"upper_ci": 1078.284506667
},
{
"lower_ci": 1073.5327980749,
"model": "qwen2-72b-instruct",
"rank": 34,
"rating": 1075.9397511888,
"upper_ci": 1077.9102798056
},
{
"lower_ci": 1073.0022184434,
"model": "gpt-4-0314",
"rank": 35,
"rating": 1074.4688060969,
"upper_ci": 1077.3841437021
},
{
"lower_ci": 1069.6849684012,
"model": "qwen-max-0428",
"rank": 36,
"rating": 1072.288830872,
"upper_ci": 1075.2788486953
},
{
"lower_ci": 1067.4064473159,
"model": "glm-4-0116",
"rank": 37,
"rating": 1072.1854778301,
"upper_ci": 1078.0278828583
},
{
"lower_ci": 1065.2785446605,
"model": "claude-3-haiku-20240307",
"rank": 38,
"rating": 1067.2876085746,
"upper_ci": 1068.5180263057
},
{
"lower_ci": 1063.4499078695,
"model": "deepseek-coder-v2",
"rank": 39,
"rating": 1066.5634197273,
"upper_ci": 1071.0372811761
},
{
"lower_ci": 1052.4060997176,
"model": "llama-3.1-8b-instruct",
"rank": 40,
"rating": 1057.2617029177,
"upper_ci": 1062.4851344029
},
{
"lower_ci": 1050.6516231153,
"model": "reka-flash-preview-20240611",
"rank": 41,
"rating": 1053.4286082128,
"upper_ci": 1056.9047978837
},
{
"lower_ci": 1049.878634752,
"model": "gpt-4-0613",
"rank": 42,
"rating": 1051.2288727429,
"upper_ci": 1053.3859970522
},
{
"lower_ci": 1047.658821981,
"model": "qwen1.5-110b-chat",
"rank": 43,
"rating": 1050.1472801797,
"upper_ci": 1054.1870464263
},
{
"lower_ci": 1043.4416581432,
"model": "yi-1.5-34b-chat",
"rank": 44,
"rating": 1046.5798307425,
"upper_ci": 1048.4870877901
},
{
"lower_ci": 1043.9717227179,
"model": "mistral-large-2402",
"rank": 45,
"rating": 1045.8549746499,
"upper_ci": 1048.6558688014
},
{
"lower_ci": 1039.8435107486,
"model": "reka-flash-21b-20240226-online",
"rank": 46,
"rating": 1044.4541273285,
"upper_ci": 1047.5722059799
},
{
"lower_ci": 1038.3457593513,
"model": "llama-3-8b-instruct",
"rank": 47,
"rating": 1040.8943517232,
"upper_ci": 1042.1727089946
},
{
"lower_ci": 1034.3532315209,
"model": "command-r",
"rank": 48,
"rating": 1037.5954245649,
"upper_ci": 1039.801976874
},
{
"lower_ci": 1033.8210405932,
"model": "claude-1",
"rank": 49,
"rating": 1037.2264989242,
"upper_ci": 1039.8445566211
},
{
"lower_ci": 1032.4181357042,
"model": "reka-flash-21b-20240226",
"rank": 50,
"rating": 1036.2083492306,
"upper_ci": 1038.9143450059
},
{
"lower_ci": 1033.5592570692,
"model": "mistral-medium",
"rank": 51,
"rating": 1035.9830773208,
"upper_ci": 1038.0506828269
},
{
"lower_ci": 1033.4716682328,
"model": "mixtral-8x22b-instruct-v0.1",
"rank": 52,
"rating": 1035.6187089038,
"upper_ci": 1037.3385699205
},
{
"lower_ci": 1032.3748800585,
"model": "qwen1.5-72b-chat",
"rank": 53,
"rating": 1035.5734020095,
"upper_ci": 1037.8584457516
},
{
"lower_ci": 1016.6859168483,
"model": "claude-2.0",
"rank": 54,
"rating": 1020.4032512576,
"upper_ci": 1023.0900087939
},
{
"lower_ci": 1016.4818650296,
"model": "gemini-pro-dev-api",
"rank": 55,
"rating": 1018.8216738996,
"upper_ci": 1022.0575603351
},
{
"lower_ci": 1013.9644553596,
"model": "gemma-2-2b-it",
"rank": 56,
"rating": 1018.7496539694,
"upper_ci": 1022.6257555787
},
{
"lower_ci": 1009.8189712109,
"model": "zephyr-orpo-141b-A35b-v0.1",
"rank": 57,
"rating": 1017.4768858149,
"upper_ci": 1023.4231756618
},
{
"lower_ci": 1011.7444717478,
"model": "qwen1.5-32b-chat",
"rank": 58,
"rating": 1014.2192047782,
"upper_ci": 1017.4848181067
},
{
"lower_ci": 1009.527805507,
"model": "mistral-next",
"rank": 59,
"rating": 1013.8190347615,
"upper_ci": 1016.756252395
},
{
"lower_ci": 1008.0043265533,
"model": "phi-3-medium-4k-instruct",
"rank": 60,
"rating": 1011.6064259691,
"upper_ci": 1014.8977711664
},
{
"lower_ci": 1003.3664596337,
"model": "claude-2.1",
"rank": 61,
"rating": 1006.9894951694,
"upper_ci": 1008.7578243389
},
{
"lower_ci": 1003.5743630599,
"model": "starling-lm-7b-beta",
"rank": 62,
"rating": 1006.9783218473,
"upper_ci": 1009.6647795891
},
{
"lower_ci": 1003.3560004715,
"model": "gpt-3.5-turbo-0613",
"rank": 63,
"rating": 1004.9730864576,
"upper_ci": 1008.7646121872
},
{
"lower_ci": 1000.3011942689,
"model": "mixtral-8x7b-instruct-v0.1",
"rank": 64,
"rating": 1002.12545233,
"upper_ci": 1004.4555563028
},
{
"lower_ci": 996.8355186436,
"model": "yi-34b-chat",
"rank": 65,
"rating": 1000.1263930743,
"upper_ci": 1002.9767969377
},
{
"lower_ci": 996.5513388826,
"model": "claude-instant-1",
"rank": 66,
"rating": 999.4536204497,
"upper_ci": 1003.0420312018
},
{
"lower_ci": 991.5815494729,
"model": "gemini-pro",
"rank": 67,
"rating": 998.3909699055,
"upper_ci": 1005.6665144072
},
{
"lower_ci": 994.5272838271,
"model": "qwen1.5-14b-chat",
"rank": 68,
"rating": 997.6714948516,
"upper_ci": 1000.3276398407
},
{
"lower_ci": 988.7882364736,
"model": "gpt-3.5-turbo-0314",
"rank": 69,
"rating": 997.4790766208,
"upper_ci": 1005.2920277339
},
{
"lower_ci": 989.2933547328,
"model": "wizardlm-70b",
"rank": 70,
"rating": 995.5069328559,
"upper_ci": 1000.0203225061
},
{
"lower_ci": 992.3677866278,
"model": "gpt-3.5-turbo-0125",
"rank": 71,
"rating": 994.221194786,
"upper_ci": 996.0922832004
},
{
"lower_ci": 989.517752069,
"model": "dbrx-instruct-preview",
"rank": 72,
"rating": 991.6558051925,
"upper_ci": 994.3414735308
},
{
"lower_ci": 988.3935167102,
"model": "phi-3-small-8k-instruct",
"rank": 73,
"rating": 990.3926872181,
"upper_ci": 993.4532484928
},
{
"lower_ci": 980.2003929739,
"model": "tulu-2-dpo-70b",
"rank": 74,
"rating": 986.8619167507,
"upper_ci": 995.6082960114
},
{
"lower_ci": 979.2393563337,
"model": "llama-2-70b-chat",
"rank": 75,
"rating": 982.0382072414,
"upper_ci": 983.1882888775
},
{
"lower_ci": 976.2082709482,
"model": "openchat-3.5-0106",
"rank": 76,
"rating": 980.6486425506,
"upper_ci": 984.7448454329
},
{
"lower_ci": 976.21123294,
"model": "vicuna-33b",
"rank": 77,
"rating": 978.8419077515,
"upper_ci": 983.0972163635
},
{
"lower_ci": 976.387496134,
"model": "snowflake-arctic-instruct",
"rank": 78,
"rating": 978.4458039182,
"upper_ci": 981.5060581663
},
{
"lower_ci": 969.5806601345,
"model": "starling-lm-7b-alpha",
"rank": 79,
"rating": 976.025808172,
"upper_ci": 980.086762811
},
{
"lower_ci": 965.8992419629,
"model": "nous-hermes-2-mixtral-8x7b-dpo",
"rank": 80,
"rating": 975.4699172429,
"upper_ci": 981.307231701
},
{
"lower_ci": 969.0894947313,
"model": "gemma-1.1-7b-it",
"rank": 81,
"rating": 971.847848073,
"upper_ci": 975.4703266199
},
{
"lower_ci": 966.6172052307,
"model": "llama2-70b-steerlm-chat",
"rank": 82,
"rating": 971.6537111318,
"upper_ci": 979.8268878882
},
{
"lower_ci": 961.617441776,
"model": "pplx-70b-online",
"rank": 83,
"rating": 967.4367908935,
"upper_ci": 972.8126406202
},
{
"lower_ci": 959.5692952959,
"model": "openchat-3.5",
"rank": 84,
"rating": 966.0510063396,
"upper_ci": 971.8466170437
},
{
"lower_ci": 956.7287406383,
"model": "deepseek-llm-67b-chat",
"rank": 85,
"rating": 965.1147523375,
"upper_ci": 971.4330625559
},
{
"lower_ci": 956.3934469962,
"model": "openhermes-2.5-mistral-7b",
"rank": 86,
"rating": 963.454411119,
"upper_ci": 968.2145476373
},
{
"lower_ci": 957.6795493747,
"model": "mistral-7b-instruct-v0.2",
"rank": 87,
"rating": 961.195768793,
"upper_ci": 964.3273838331
},
{
"lower_ci": 955.9914563912,
"model": "qwen1.5-7b-chat",
"rank": 88,
"rating": 959.7566395303,
"upper_ci": 963.8434392791
},
{
"lower_ci": 953.2396686903,
"model": "phi-3-mini-4k-instruct-june-2024",
"rank": 89,
"rating": 958.8907631692,
"upper_ci": 964.0199135738
},
{
"lower_ci": 953.2564762147,
"model": "gpt-3.5-turbo-1106",
"rank": 90,
"rating": 955.8557887224,
"upper_ci": 959.2854635955
},
{
"lower_ci": 951.2318268117,
"model": "phi-3-mini-4k-instruct",
"rank": 91,
"rating": 955.5964299136,
"upper_ci": 958.4767635868
},
{
"lower_ci": 939.9598426545,
"model": "dolphin-2.2.1-mistral-7b",
"rank": 92,
"rating": 952.2051167375,
"upper_ci": 962.2676381777
},
{
"lower_ci": 945.2431328588,
"model": "solar-10.7b-instruct-v1.0",
"rank": 93,
"rating": 951.1224233106,
"upper_ci": 958.6524028214
},
{
"lower_ci": 948.6812080723,
"model": "llama-2-13b-chat",
"rank": 94,
"rating": 951.0465511917,
"upper_ci": 953.7276982632
},
{
"lower_ci": 940.2487365654,
"model": "wizardlm-13b",
"rank": 95,
"rating": 945.6170139554,
"upper_ci": 952.3153173674
},
{
"lower_ci": 937.3497020159,
"model": "zephyr-7b-beta",
"rank": 96,
"rating": 941.7856240916,
"upper_ci": 945.7193614882
},
{
"lower_ci": 925.3514960917,
"model": "mpt-30b-chat",
"rank": 97,
"rating": 933.4637447927,
"upper_ci": 942.1936901157
},
{
"lower_ci": 928.7552755121,
"model": "pplx-7b-online",
"rank": 98,
"rating": 932.9740226673,
"upper_ci": 940.2890736975
},
{
"lower_ci": 924.8240945839,
"model": "codellama-34b-instruct",
"rank": 99,
"rating": 931.25075507,
"upper_ci": 936.6721012017
},
{
"lower_ci": 919.9794338309,
"model": "zephyr-7b-alpha",
"rank": 100,
"rating": 930.8024303718,
"upper_ci": 940.3904190626
},
{
"lower_ci": 927.6228696967,
"model": "vicuna-13b",
"rank": 101,
"rating": 930.129806663,
"upper_ci": 933.8873904378
},
{
"lower_ci": 916.3079081804,
"model": "codellama-70b-instruct",
"rank": 102,
"rating": 929.7441814853,
"upper_ci": 939.4638589466
},
{
"lower_ci": 919.0275736817,
"model": "gemma-7b-it",
"rank": 103,
"rating": 925.6063141152,
"upper_ci": 931.2321796245
},
{
"lower_ci": 921.4335696267,
"model": "llama-2-7b-chat",
"rank": 104,
"rating": 925.1226871516,
"upper_ci": 927.4211774328
},
{
"lower_ci": 919.914948524,
"model": "phi-3-mini-128k-instruct",
"rank": 105,
"rating": 925.0941128748,
"upper_ci": 928.953409783
},
{
"lower_ci": 917.0649637172,
"model": "qwen-14b-chat",
"rank": 106,
"rating": 923.0565707958,
"upper_ci": 927.5147584562
},
{
"lower_ci": 910.6316722798,
"model": "falcon-180b-chat",
"rank": 107,
"rating": 922.8642075646,
"upper_ci": 938.170426621
},
{
"lower_ci": 912.8204058608,
"model": "guanaco-33b",
"rank": 108,
"rating": 921.0201740806,
"upper_ci": 929.2566479601
},
{
"lower_ci": 903.2450471973,
"model": "gemma-1.1-2b-it",
"rank": 109,
"rating": 908.7494526802,
"upper_ci": 913.4741035764
},
{
"lower_ci": 899.9846491667,
"model": "stripedhyena-nous-7b",
"rank": 110,
"rating": 905.1534113535,
"upper_ci": 912.9382997405
},
{
"lower_ci": 899.9839053334,
"model": "olmo-7b-instruct",
"rank": 111,
"rating": 903.629872537,
"upper_ci": 908.2570306538
},
{
"lower_ci": 890.8398870858,
"model": "mistral-7b-instruct",
"rank": 112,
"rating": 897.2720855909,
"upper_ci": 902.9292885859
},
{
"lower_ci": 887.0047037055,
"model": "vicuna-7b",
"rank": 113,
"rating": 893.825818387,
"upper_ci": 899.7593423485
},
{
"lower_ci": 887.0036385995,
"model": "palm-2",
"rank": 114,
"rating": 891.3072880052,
"upper_ci": 897.1963496269
},
{
"lower_ci": 872.1578125039,
"model": "gemma-2b-it",
"rank": 115,
"rating": 880.4830688196,
"upper_ci": 884.0952002573
},
{
"lower_ci": 868.4676861275,
"model": "qwen1.5-4b-chat",
"rank": 116,
"rating": 877.0664166393,
"upper_ci": 883.3511645246
},
{
"lower_ci": 846.7609834499,
"model": "koala-13b",
"rank": 117,
"rating": 852.5741703315,
"upper_ci": 859.5370102373
},
{
"lower_ci": 833.5366986653,
"model": "chatglm3-6b",
"rank": 118,
"rating": 843.5467457427,
"upper_ci": 853.6979083485
},
{
"lower_ci": 808.672593832,
"model": "gpt4all-13b-snoozy",
"rank": 119,
"rating": 821.0385947815,
"upper_ci": 835.6716204673
},
{
"lower_ci": 804.1197078456,
"model": "chatglm2-6b",
"rank": 120,
"rating": 815.3737962537,
"upper_ci": 821.0889058237
},
{
"lower_ci": 805.0790145038,
"model": "mpt-7b-chat",
"rank": 121,
"rating": 813.8798502443,
"upper_ci": 823.374846381
},
{
"lower_ci": 803.3055604626,
"model": "RWKV-4-Raven-14B",
"rank": 122,
"rating": 810.0683748343,
"upper_ci": 819.7203248755
},
{
"lower_ci": 781.8369679949,
"model": "alpaca-13b",
"rank": 123,
"rating": 789.0910768147,
"upper_ci": 797.3012759671
},
{
"lower_ci": 778.7113024193,
"model": "oasst-pythia-12b",
"rank": 124,
"rating": 782.6327874047,
"upper_ci": 789.0013974908
},
{
"lower_ci": 760.5962982346,
"model": "chatglm-6b",
"rank": 125,
"rating": 767.7699631784,
"upper_ci": 776.2247501319
},
{
"lower_ci": 749.711207841,
"model": "fastchat-t5-3b",
"rank": 126,
"rating": 756.8214872887,
"upper_ci": 762.6617679978
},
{
"lower_ci": 723.1589751426,
"model": "stablelm-tuned-alpha-7b",
"rank": 127,
"rating": 727.6986691281,
"upper_ci": 737.7996673488
},
{
"lower_ci": 701.8523006848,
"model": "dolly-v2-12b",
"rank": 128,
"rating": 710.1023148692,
"upper_ci": 717.2721178625
},
{
"lower_ci": 679.2645194103,
"model": "llama-13b",
"rank": 129,
"rating": 689.1631346499,
"upper_ci": 694.5590720343
}
]