diff options
Diffstat (limited to 'benchmark/reports/mini-agi/5.2_TestRevenueRetrieval_1.0.json')
-rw-r--r-- | benchmark/reports/mini-agi/5.2_TestRevenueRetrieval_1.0.json | 31 |
1 files changed, 31 insertions, 0 deletions
diff --git a/benchmark/reports/mini-agi/5.2_TestRevenueRetrieval_1.0.json b/benchmark/reports/mini-agi/5.2_TestRevenueRetrieval_1.0.json new file mode 100644 index 000000000..f8eaa4007 --- /dev/null +++ b/benchmark/reports/mini-agi/5.2_TestRevenueRetrieval_1.0.json @@ -0,0 +1,31 @@ +{ + "command": "agbenchmark start --test TestRevenueRetrieval_1.0", + "completion_time": "2023-07-24-13:22", + "metrics": { + "run_time": "33.64 seconds", + "highest_difficulty": "novice: 3" + }, + "tests": { + "TestRevenueRetrieval_1.0": { + "data_path": "agbenchmark/challenges/retrieval/r2_search_suite_1/1_tesla_revenue/data.json", + "is_regression": true, + "category": [ + "retrieval", + "retrieval" + ], + "task": "Write tesla's exact revenue in 2022 into a .txt file. Use the US notation, with a precision rounded to the nearest million dollars (for instance, $31,578 billion).", + "answer": "It was $81.462 billion in 2022.", + "description": "A no guardrails search for info", + "metrics": { + "difficulty": "novice", + "success": true, + "success_%": 100.0, + "run_time": "33.13 seconds" + }, + "reached_cutoff": false + } + }, + "config": { + "workspace": "${os.path.join(Path.home(), 'miniagi')}" + } +}
\ No newline at end of file |