diff options
Diffstat (limited to 'benchmark/reports/mini-agi/7.1_TestRevenueRetrieval_1.2.json')
-rw-r--r-- | benchmark/reports/mini-agi/7.1_TestRevenueRetrieval_1.2.json | 31 |
1 files changed, 31 insertions, 0 deletions
diff --git a/benchmark/reports/mini-agi/7.1_TestRevenueRetrieval_1.2.json b/benchmark/reports/mini-agi/7.1_TestRevenueRetrieval_1.2.json new file mode 100644 index 000000000..99373f7f1 --- /dev/null +++ b/benchmark/reports/mini-agi/7.1_TestRevenueRetrieval_1.2.json @@ -0,0 +1,31 @@ +{ + "command": "agbenchmark start --test TestRetrieval2.2", + "completion_time": "2023-07-17-17:57", + "metrics": { + "run_time": "31.1 seconds", + "highest_difficulty": "No successful tests" + }, + "tests": { + "TestRetrieval2.2": { + "data_path": "agbenchmark/challenges/retrieval/r2.2_formatting", + "is_regression": false, + "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 $81.462 billion in 2022. In millions the answer is 81,462.", + "description": "Advanced version of the r2.1 challenge that also asks for specific formatting.", + "metrics": { + "difficulty": "intermediate", + "success": false, + "fail_reason": "assert 1 in [0.0]", + "success_%": 0.0, + "run_time": "30.888 seconds" + }, + "reached_cutoff": false + } + }, + "config": { + "workspace": "${os.path.join(Path.home(), 'miniagi')}" + }, + "additional": { + "model": "gpt-4" + } +} |