liqiang/ai-agent-book
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

ai-agent-book 精选快照（<2MB 代码与文档，来自 github.com/bojieli/ai-agent-book）
Build latest book artifacts / build (push) Canceled after 0s
Details
dependency resolution / resolve (3.11) (push) Canceled after 0s
Details
dependency resolution / resolve (3.13) (push) Canceled after 0s
Details
deploy-pages / build (push) Canceled after 0s
Details
deploy-pages / deploy (push) Canceled after 0s
Details
i18n consistency check / check (push) Canceled after 0s
Details
provider adoption tests / test (chapter2/context-compression) (push) Canceled after 0s
Details
provider adoption tests / test (chapter2/prompt-injection) (push) Canceled after 0s
Details
provider adoption tests / test (chapter2/system-hint) (push) Canceled after 0s
Details
provider adoption tests / test (chapter3/log-sanitization) (push) Canceled after 0s
Details
web-search-agent tests / test (push) Canceled after 0s
Details
web-search-agent tests / agentbook (push) Canceled after 0s
Details

Browse Source
This commit is contained in:
liqiang
2026-08-20 13:12:50 +00:00
commit b119135836
10275 changed files with 3284984 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
chapter7/elo-leaderboard/validation/runs/exp7-7-arena-20260731-v1/online_elo.json
+905
View File
@@ -0,0 +1,905 @@
[
{
"matches": 55654,
"model": "gemini-1.5-pro-api-0409-preview",
"rank": 1,
"rating": 1159.8203895968,
"wins": 33738.5
},
{
"matches": 20071,
"model": "gemini-1.5-pro-exp-0801",
"rank": 2,
"rating": 1127.8877886511,
"wins": 12139.5
},
{
"matches": 14514,
"model": "chatgpt-4o-latest",
"rank": 3,
"rating": 1126.6935165964,
"wins": 8999.0
},
{
"matches": 5655,
"model": "gpt-3.5-turbo-0314",
"rank": 4,
"rating": 1103.9751202512,
"wins": 3789.0
},
{
"matches": 11827,
"model": "bard-jan-24-gemini-pro",
"rank": 5,
"rating": 1094.2118678517,
"wins": 7075.5
},
{
"matches": 21172,
"model": "claude-1",
"rank": 6,
"rating": 1092.7309868534,
"wins": 12081.5
},
{
"matches": 52155,
"model": "gemini-advanced-0514",
"rank": 7,
"rating": 1087.5408038371,
"wins": 30523.0
},
{
"matches": 13604,
"model": "llama-3.1-70b-instruct",
"rank": 8,
"rating": 1087.3529845908,
"wins": 7058.5
},
{
"matches": 77509,
"model": "gpt-4o-2024-05-13",
"rank": 9,
"rating": 1086.7242770205,
"wins": 46951.0
},
{
"matches": 9761,
"model": "gpt-4o-2024-08-06",
"rank": 10,
"rating": 1085.601246973,
"wins": 5323.0
},
{
"matches": 19370,
"model": "gpt-4o-mini-2024-07-18",
"rank": 11,
"rating": 1079.187026245,
"wins": 11082.0
},
{
"matches": 47703,
"model": "claude-3-5-sonnet-20240620",
"rank": 12,
"rating": 1079.0096726066,
"wins": 27107.5
},
{
"matches": 155944,
"model": "claude-3-opus-20240229",
"rank": 13,
"rating": 1074.9078256001,
"wins": 91432.5
},
{
"matches": 11476,
"model": "athene-70b-0725",
"rank": 14,
"rating": 1073.7607622933,
"wins": 6098.0
},
{
"matches": 18790,
"model": "gemini-pro-dev-api",
"rank": 15,
"rating": 1072.3072263884,
"wins": 8728.5
},
{
"matches": 12774,
"model": "claude-2.0",
"rank": 16,
"rating": 1069.530762176,
"wins": 6814.5
},
{
"matches": 10239,
"model": "glm-4-0520",
"rank": 17,
"rating": 1065.2967580553,
"wins": 5154.5
},
{
"matches": 20669,
"model": "nemotron-4-340b-instruct",
"rank": 18,
"rating": 1063.9797181947,
"wins": 10567.5
},
{
"matches": 51739,
"model": "yi-large-preview",
"rank": 19,
"rating": 1060.8561460851,
"wins": 28793.0
},
{
"matches": 39631,
"model": "llama-2-70b-chat",
"rank": 20,
"rating": 1060.6350445555,
"wins": 18272.0
},
{
"matches": 6974,
"model": "reka-core-20240722",
"rank": 21,
"rating": 1059.9327626435,
"wins": 3490.0
},
{
"matches": 69418,
"model": "gemini-1.5-pro-api-0514",
"rank": 22,
"rating": 1059.8892020659,
"wins": 39302.5
},
{
"matches": 6565,
"model": "gemini-pro",
"rank": 23,
"rating": 1059.2020149016,
"wins": 3028.0
},
{
"matches": 18897,
"model": "llama-3.1-405b-instruct",
"rank": 24,
"rating": 1058.4003562569,
"wins": 10361.5
},
{
"matches": 11517,
"model": "mistral-large-2407",
"rank": 25,
"rating": 1058.1277726399,
"wins": 6038.5
},
{
"matches": 84505,
"model": "gpt-4-turbo-2024-04-09",
"rank": 26,
"rating": 1054.9014485987,
"wins": 48844.5
},
{
"matches": 92488,
"model": "gpt-4-1106-preview",
"rank": 27,
"rating": 1054.2069148591,
"wins": 57496.5
},
{
"matches": 38959,
"model": "gpt-3.5-turbo-0613",
"rank": 28,
"rating": 1052.6707187439,
"wins": 19308.0
},
{
"matches": 85867,
"model": "gpt-4-0125-preview",
"rank": 29,
"rating": 1050.1218586343,
"wins": 50802.5
},
{
"matches": 7579,
"model": "glm-4-0116",
"rank": 30,
"rating": 1049.1894798578,
"wins": 3566.0
},
{
"matches": 4858,
"model": "zephyr-orpo-141b-A35b-v0.1",
"rank": 31,
"rating": 1045.2216087838,
"wins": 2116.5
},
{
"matches": 25748,
"model": "qwen-max-0428",
"rank": 32,
"rating": 1044.8335252342,
"wins": 12269.5
},
{
"matches": 20633,
"model": "claude-instant-1",
"rank": 33,
"rating": 1044.7562986355,
"wins": 11178.0
},
{
"matches": 16672,
"model": "yi-large",
"rank": 34,
"rating": 1044.7374546104,
"wins": 8533.5
},
{
"matches": 3997,
"model": "deepseek-coder-v2-0724",
"rank": 35,
"rating": 1043.8935002553,
"wins": 1883.5
},
{
"matches": 16165,
"model": "deepseek-v2-api-0628",
"rank": 36,
"rating": 1042.4852039574,
"wins": 7994.5
},
{
"matches": 56129,
"model": "gemini-1.5-flash-api-0514",
"rank": 37,
"rating": 1041.3766839839,
"wins": 29778.0
},
{
"matches": 161827,
"model": "llama-3-70b-instruct",
"rank": 38,
"rating": 1040.8719399645,
"wins": 84977.0
},
{
"matches": 80911,
"model": "command-r-plus",
"rank": 39,
"rating": 1034.8822379837,
"wins": 40967.0
},
{
"matches": 55979,
"model": "gpt-4-0314",
"rank": 40,
"rating": 1033.6412751608,
"wins": 31098.0
},
{
"matches": 37702,
"model": "claude-2.1",
"rank": 41,
"rating": 1032.8143823524,
"wins": 16848.0
},
{
"matches": 8391,
"model": "wizardlm-70b",
"rank": 42,
"rating": 1032.5111769139,
"wins": 4325.0
},
{
"matches": 27838,
"model": "gemma-2-27b-it",
"rank": 43,
"rating": 1030.7976774989,
"wins": 13981.5
},
{
"matches": 1714,
"model": "dolphin-2.2.1-mistral-7b",
"rank": 44,
"rating": 1029.9575607586,
"wins": 738.5
},
{
"matches": 3003,
"model": "guanaco-33b",
"rank": 45,
"rating": 1027.2582838587,
"wins": 1552.0
},
{
"matches": 3843,
"model": "nous-hermes-2-mixtral-8x7b-dpo",
"rank": 46,
"rating": 1025.2145335894,
"wins": 1697.5
},
{
"matches": 7192,
"model": "wizardlm-13b",
"rank": 47,
"rating": 1024.793903105,
"wins": 3690.0
},
{
"matches": 2650,
"model": "mpt-30b-chat",
"rank": 48,
"rating": 1024.0563241095,
"wins": 1351.5
},
{
"matches": 27508,
"model": "qwen1.5-110b-chat",
"rank": 49,
"rating": 1023.7761579902,
"wins": 12612.0
},
{
"matches": 113106,
"model": "claude-3-sonnet-20240229",
"rank": 50,
"rating": 1023.6338810846,
"wins": 60284.5
},
{
"matches": 12377,
"model": "mistral-next",
"rank": 51,
"rating": 1021.9755255724,
"wins": 5952.5
},
{
"matches": 15801,
"model": "deepseek-coder-v2",
"rank": 52,
"rating": 1021.6778455715,
"wins": 7243.0
},
{
"matches": 16056,
"model": "reka-flash-21b-20240226-online",
"rank": 53,
"rating": 1020.8238893282,
"wins": 7554.5
},
{
"matches": 16667,
"model": "starling-lm-7b-beta",
"rank": 54,
"rating": 1020.1246920766,
"wins": 7626.0
},
{
"matches": 3636,
"model": "llama2-70b-steerlm-chat",
"rank": 55,
"rating": 1018.5882277478,
"wins": 1587.5
},
{
"matches": 35555,
"model": "mistral-medium",
"rank": 56,
"rating": 1018.0043978294,
"wins": 17731.5
},
{
"matches": 19740,
"model": "llama-2-13b-chat",
"rank": 57,
"rating": 1016.6652779795,
"wins": 8935.5
},
{
"matches": 6660,
"model": "tulu-2-dpo-70b",
"rank": 58,
"rating": 1014.6804751782,
"wins": 3231.0
},
{
"matches": 62688,
"model": "reka-core-20240501",
"rank": 59,
"rating": 1013.8222528866,
"wins": 31198.0
},
{
"matches": 89617,
"model": "gpt-4-0613",
"rank": 60,
"rating": 1013.3276942754,
"wins": 43878.0
},
{
"matches": 4981,
"model": "deepseek-llm-67b-chat",
"rank": 61,
"rating": 1011.6783077357,
"wins": 2017.0
},
{
"matches": 4291,
"model": "solar-10.7b-instruct-v1.0",
"rank": 62,
"rating": 1011.6055213958,
"wins": 1814.0
},
{
"matches": 12987,
"model": "openchat-3.5-0106",
"rank": 63,
"rating": 1009.5145969972,
"wins": 5974.0
},
{
"matches": 7156,
"model": "reka-flash-20240722",
"rank": 64,
"rating": 1003.5048766039,
"wins": 3290.0
},
{
"matches": 25248,
"model": "gemma-2-9b-it",
"rank": 65,
"rating": 1003.026164166,
"wins": 11661.5
},
{
"matches": 12671,
"model": "llama-3.1-8b-instruct",
"rank": 66,
"rating": 1002.2631876345,
"wins": 5121.0
},
{
"matches": 8117,
"model": "openchat-3.5",
"rank": 67,
"rating": 1001.939993772,
"wins": 3783.0
},
{
"matches": 6338,
"model": "pplx-7b-online",
"rank": 68,
"rating": 1001.6927968751,
"wins": 2572.0
},
{
"matches": 40643,
"model": "qwen1.5-72b-chat",
"rank": 69,
"rating": 1000.9425509065,
"wins": 19941.0
},
{
"matches": 1815,
"model": "zephyr-7b-alpha",
"rank": 70,
"rating": 999.8845726251,
"wins": 855.0
},
{
"matches": 109888,
"model": "claude-3-haiku-20240307",
"rank": 71,
"rating": 999.7072031054,
"wins": 55074.0
},
{
"matches": 10422,
"model": "starling-lm-7b-alpha",
"rank": 72,
"rating": 998.0936577805,
"wins": 4817.0
},
{
"matches": 25792,
"model": "reka-flash-21b-20240226",
"rank": 73,
"rating": 992.8107482264,
"wins": 11891.0
},
{
"matches": 64938,
"model": "mistral-large-2402",
"rank": 74,
"rating": 992.5035561283,
"wins": 30754.5
},
{
"matches": 17026,
"model": "gpt-3.5-turbo-1106",
"rank": 75,
"rating": 990.5828502496,
"wins": 7026.0
},
{
"matches": 4864,
"model": "qwen1.5-7b-chat",
"rank": 76,
"rating": 990.5290268684,
"wins": 1903.5
},
{
"matches": 20477,
"model": "reka-flash-preview-20240611",
"rank": 77,
"rating": 990.4289024537,
"wins": 9003.5
},
{
"matches": 25156,
"model": "yi-1.5-34b-chat",
"rank": 78,
"rating": 988.8079557694,
"wins": 11066.0
},
{
"matches": 5091,
"model": "openhermes-2.5-mistral-7b",
"rank": 79,
"rating": 988.507956639,
"wins": 2379.0
},
{
"matches": 7508,
"model": "codellama-34b-instruct",
"rank": 80,
"rating": 986.9963372601,
"wins": 3192.5
},
{
"matches": 18666,
"model": "qwen1.5-14b-chat",
"rank": 81,
"rating": 985.79676379,
"wins": 8265.0
},
{
"matches": 15946,
"model": "yi-34b-chat",
"rank": 82,
"rating": 984.9789753527,
"wins": 7423.5
},
{
"matches": 6890,
"model": "pplx-70b-online",
"rank": 83,
"rating": 984.0082457269,
"wins": 3118.0
},
{
"matches": 34410,
"model": "qwen2-72b-instruct",
"rank": 84,
"rating": 983.7228839439,
"wins": 16578.5
},
{
"matches": 33736,
"model": "dbrx-instruct-preview",
"rank": 85,
"rating": 983.0655232047,
"wins": 14350.5
},
{
"matches": 107100,
"model": "llama-3-8b-instruct",
"rank": 86,
"rating": 978.2506897907,
"wins": 49020.5
},
{
"matches": 1325,
"model": "falcon-180b-chat",
"rank": 87,
"rating": 976.0053410687,
"wins": 580.0
},
{
"matches": 8745,
"model": "palm-2",
"rank": 88,
"rating": 975.4724123669,
"wins": 3851.5
},
{
"matches": 5070,
"model": "qwen-14b-chat",
"rank": 89,
"rating": 974.4393986925,
"wins": 2262.5
},
{
"matches": 5270,
"model": "stripedhyena-nous-7b",
"rank": 90,
"rating": 972.5214538963,
"wins": 2001.0
},
{
"matches": 22783,
"model": "qwen1.5-32b-chat",
"rank": 91,
"rating": 970.5573357551,
"wins": 10038.5
},
{
"matches": 56373,
"model": "command-r",
"rank": 92,
"rating": 968.3429828775,
"wins": 25830.5
},
{
"matches": 9178,
"model": "gemma-7b-it",
"rank": 93,
"rating": 966.2526965022,
"wins": 3447.5
},
{
"matches": 11330,
"model": "zephyr-7b-beta",
"rank": 94,
"rating": 966.1969243012,
"wins": 5268.0
},
{
"matches": 50256,
"model": "mixtral-8x22b-instruct-v0.1",
"rank": 95,
"rating": 964.4141739849,
"wins": 22236.0
},
{
"matches": 7022,
"model": "vicuna-7b",
"rank": 96,
"rating": 963.6362226151,
"wins": 3187.5
},
{
"matches": 34197,
"model": "snowflake-arctic-instruct",
"rank": 97,
"rating": 961.9084215198,
"wins": 13326.5
},
{
"matches": 22938,
"model": "vicuna-33b",
"rank": 98,
"rating": 959.3823284501,
"wins": 10924.5
},
{
"matches": 10509,
"model": "gemma-2-2b-it",
"rank": 99,
"rating": 959.2713799268,
"wins": 3731.5
},
{
"matches": 7038,
"model": "koala-13b",
"rank": 100,
"rating": 954.395027749,
"wins": 3380.0
},
{
"matches": 68914,
"model": "gpt-3.5-turbo-0125",
"rank": 101,
"rating": 951.9181205239,
"wins": 29165.5
},
{
"matches": 9145,
"model": "mistral-7b-instruct",
"rank": 102,
"rating": 948.891187234,
"wins": 3685.5
},
{
"matches": 14559,
"model": "llama-2-7b-chat",
"rank": 103,
"rating": 948.4212635676,
"wins": 6212.0
},
{
"matches": 20074,
"model": "mistral-7b-instruct-v0.2",
"rank": 104,
"rating": 945.8420359878,
"wins": 8282.5
},
{
"matches": 25095,
"model": "gemma-1.1-7b-it",
"rank": 105,
"rating": 941.8141470663,
"wins": 9687.0
},
{
"matches": 1787,
"model": "gpt4all-13b-snoozy",
"rank": 106,
"rating": 938.6958755482,
"wins": 680.0
},
{
"matches": 18505,
"model": "phi-3-small-8k-instruct",
"rank": 107,
"rating": 930.6944270029,
"wins": 7100.0
},
{
"matches": 6496,
"model": "olmo-7b-instruct",
"rank": 108,
"rating": 928.8306135323,
"wins": 2157.0
},
{
"matches": 21129,
"model": "phi-3-mini-4k-instruct",
"rank": 109,
"rating": 928.4371869598,
"wins": 7094.0
},
{
"matches": 21617,
"model": "phi-3-mini-128k-instruct",
"rank": 110,
"rating": 928.3336295806,
"wins": 7094.5
},
{
"matches": 4938,
"model": "RWKV-4-Raven-14B",
"rank": 111,
"rating": 927.486785137,
"wins": 1965.5
},
{
"matches": 19794,
"model": "vicuna-13b",
"rank": 112,
"rating": 927.1632498042,
"wins": 9553.5
},
{
"matches": 1193,
"model": "codellama-70b-instruct",
"rank": 113,
"rating": 926.7141337337,
"wins": 411.5
},
{
"matches": 4018,
"model": "mpt-7b-chat",
"rank": 114,
"rating": 922.0268289601,
"wins": 1573.5
},
{
"matches": 76064,
"model": "mixtral-8x7b-instruct-v0.1",
"rank": 115,
"rating": 920.8542542685,
"wins": 33437.0
},
{
"matches": 22427,
"model": "phi-3-medium-4k-instruct",
"rank": 116,
"rating": 919.7045738753,
"wins": 8854.0
},
{
"matches": 4921,
"model": "gemma-2b-it",
"rank": 117,
"rating": 918.581510353,
"wins": 1513.0
},
{
"matches": 10484,
"model": "phi-3-mini-4k-instruct-june-2024",
"rank": 118,
"rating": 913.3885931532,
"wins": 3097.5
},
{
"matches": 7811,
"model": "qwen1.5-4b-chat",
"rank": 119,
"rating": 910.8121423587,
"wins": 2364.5
},
{
"matches": 4995,
"model": "chatglm-6b",
"rank": 120,
"rating": 908.8611775605,
"wins": 1834.5
},
{
"matches": 5874,
"model": "alpaca-13b",
"rank": 121,
"rating": 904.2619553966,
"wins": 2330.0
},
{
"matches": 11363,
"model": "gemma-1.1-2b-it",
"rank": 122,
"rating": 892.2955737397,
"wins": 3282.0
},
{
"matches": 2707,
"model": "chatglm2-6b",
"rank": 123,
"rating": 888.2580854124,
"wins": 808.0
},
{
"matches": 3334,
"model": "stablelm-tuned-alpha-7b",
"rank": 124,
"rating": 882.7115402984,
"wins": 1141.5
},
{
"matches": 4763,
"model": "chatglm3-6b",
"rank": 125,
"rating": 867.498613261,
"wins": 1454.0
},
{
"matches": 6382,
"model": "oasst-pythia-12b",
"rank": 126,
"rating": 865.3424632797,
"wins": 2425.0
},
{
"matches": 2443,
"model": "llama-13b",
"rank": 127,
"rating": 852.9506118392,
"wins": 745.5
},
{
"matches": 4304,
"model": "fastchat-t5-3b",
"rank": 128,
"rating": 847.3254654092,
"wins": 1465.0
},
{
"matches": 3484,
"model": "dolly-v2-12b",
"rank": 129,
"rating": 834.3876685486,
"wins": 1099.5
}
]