developer_uid: chai_backend_admin
submission_id: function_bekus_2026-01-19
model_name: abtest_tai
model_group:
status: torndown
timestamp: 2026-01-22T17:18:19+00:00
num_battles: 11831
num_wins: 6041
celo_rating: 1310.68
family_friendly_score: 0.5474
family_friendly_standard_error: 0.00703922211611482
submission_type: function
display_name: abtest_tai
is_internal_developer: True
ranking_group: single
us_pacific_date: 2026-01-19
win_ratio: 0.5106077254669935
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '### Instruction:\n{memory}\n', 'prompt_template': '### Input:\n{prompt}\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '### Response:\n{bot_name}:', 'truncate_by_message': False}
Resubmit model
Shutdown handler not registered because Python interpreter is not running in the main thread
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
run pipeline %s
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
run pipeline stage %s
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Running pipeline stage StressChecker
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Received healthy response to inference request in 2.1896262168884277s
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Received healthy response to inference request in 1.9325721263885498s
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Received healthy response to inference request in 2.1682705879211426s
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Received healthy response to inference request in 1.7938477993011475s
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Received healthy response to inference request in 1.836211919784546s
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Received healthy response to inference request in 2.2608280181884766s
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Received healthy response to inference request in 3.4435129165649414s
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Received healthy response to inference request in 1.1513066291809082s
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Received healthy response to inference request in 1.4621477127075195s
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Received healthy response to inference request in 2.6880741119384766s
10 requests
Falling back to EndpointApi.from_submission implementation
0 failed requests
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
5th percentile: 1.2911851167678834
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
10th percentile: 1.4310636043548584
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
20th percentile: 1.7275077819824218
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
30th percentile: 1.8235026836395263
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
40th percentile: 1.8940280437469483
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
50th percentile: 2.050421357154846
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
60th percentile: 2.176812839508057
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
70th percentile: 2.2109867572784423
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
80th percentile: 2.3462772369384766
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
90th percentile: 2.7636179924011226
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
95th percentile: 3.1035654544830313
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
99th percentile: 3.3755234241485597
mean time: 2.0926398038864136
Pipeline stage StressChecker completed in 28.86s
Falling back to EndpointApi.from_submission implementation
run pipeline stage %s
Falling back to EndpointApi.from_submission implementation
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
run_pipeline:run_in_cloud %s
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
starting trigger_guanaco_pipeline args=%s
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
Falling back to EndpointApi.from_submission implementation
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 1.55s
Shutdown handler de-registered
function_bekus_2026-01-19 status is now deployed due to DeploymentManager action
Falling back to EndpointApi.from_submission implementation
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Generating Leaderboard row for %s
Generated Leaderboard row for %s
Pipeline stage OfflineFamilyFriendlyScorer completed in 2192.99s
Shutdown handler de-registered
function_bekus_2026-01-19 status is now inactive due to auto deactivation removed underperforming models
function_bekus_2026-01-19 status is now torndown due to DeploymentManager action