Files
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

388 lines
10 KiB
JSON

{
"dataset": {
"accepted_records": 1670250,
"bounded_test_run": false,
"bytes": 2131976365,
"end_utc": "2024-08-14T19:52:53.409200+00:00",
"load_filter_seconds": 15.133,
"model_count": 129,
"outcomes": {
"model_a": 543065,
"model_b": 550810,
"tie": 281121,
"tie (bothbad)": 295254
},
"path_recorded_as": "arena_data.json",
"sha256": "747c1c937dfa941d5a455a1fd70e2879d29642058da39b97996b977233b9bd1b",
"source_records": 1799991,
"start_utc": "2023-04-24T15:53:11.132200+00:00",
"url": "https://storage.googleapis.com/arena_external_data/public/clean_battle_20240814_public.json"
},
"experiment": "7-7",
"gates": {
"bradley_terry_official_method_completed": true,
"chronological_online_elo_k4_completed": true,
"d3_animation_saved": true,
"millions_of_blind_votes_loaded": true,
"monthly_history_saved": true,
"official_public_arena_snapshot_hashed": true,
"online_vs_official_method_rank_agreement_observed": true,
"pairwise_empirical_and_predicted_matrix_saved": true,
"static_visualizations_saved": true
},
"generated_at_utc": "2026-07-31T09:59:17.815099+00:00",
"official_complete": true,
"protocol": {
"bootstrap_random_seed": 0,
"bootstrap_rounds": 20,
"history_interval": "monthly cumulative snapshots",
"official_method": "Bradley-Terry maximum-likelihood reconstruction",
"online_elo": "initial=1000, K=4, stable chronological order"
},
"results": {
"official_method_top_20": [
{
"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
}
],
"online_top_20": [
{
"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
}
],
"rank_comparison": {
"claim_boundary": "This is a same-snapshot reconstruction of the official method, not a scrape of the mutable live leaderboard. Scores need not match the live service.",
"common_models": 129,
"comparison_target": "Bradley-Terry MLE reconstruction used by Chatbot Arena",
"kendall_rank_correlation": 0.606347,
"official_method_top_20": [
"chatgpt-4o-latest",
"gemini-1.5-pro-exp-0801",
"gpt-4o-2024-05-13",
"gpt-4o-mini-2024-07-18",
"claude-3-5-sonnet-20240620",
"gemini-advanced-0514",
"llama-3.1-405b-instruct",
"gpt-4o-2024-08-06",
"gemini-1.5-pro-api-0514",
"gemini-1.5-pro-api-0409-preview",
"gpt-4-turbo-2024-04-09",
"gpt-4-1106-preview",
"mistral-large-2407",
"athene-70b-0725",
"claude-3-opus-20240229",
"llama-3.1-70b-instruct",
"gpt-4-0125-preview",
"yi-large-preview",
"reka-core-20240722",
"gemini-1.5-flash-api-0514"
],
"online_top_20": [
"gemini-1.5-pro-api-0409-preview",
"gemini-1.5-pro-exp-0801",
"chatgpt-4o-latest",
"gpt-3.5-turbo-0314",
"bard-jan-24-gemini-pro",
"claude-1",
"gemini-advanced-0514",
"llama-3.1-70b-instruct",
"gpt-4o-2024-05-13",
"gpt-4o-2024-08-06",
"gpt-4o-mini-2024-07-18",
"claude-3-5-sonnet-20240620",
"claude-3-opus-20240229",
"athene-70b-0725",
"gemini-pro-dev-api",
"claude-2.0",
"glm-4-0520",
"nemotron-4-340b-instruct",
"yi-large-preview",
"llama-2-70b-chat"
],
"spearman_rank_correlation": 0.786717,
"top_20_overlap": 12
}
},
"schema_version": 1,
"status": "passed",
"timing_seconds": {
"bradley_terry": 71.472,
"online_and_history": 8.301,
"total": 97.248
}
}