diff options
Diffstat (limited to 'benchmark/agbenchmark/challenges/verticals/data/5_answer_question_csv/data.json')
-rw-r--r-- | benchmark/agbenchmark/challenges/verticals/data/5_answer_question_csv/data.json | 31 |
1 files changed, 31 insertions, 0 deletions
diff --git a/benchmark/agbenchmark/challenges/verticals/data/5_answer_question_csv/data.json b/benchmark/agbenchmark/challenges/verticals/data/5_answer_question_csv/data.json new file mode 100644 index 000000000..24b7179d8 --- /dev/null +++ b/benchmark/agbenchmark/challenges/verticals/data/5_answer_question_csv/data.json @@ -0,0 +1,31 @@ +{ + "category": [ + "data" + ], + "cutoff": 90, + "dependencies": [ + "TestAnswerQuestionSmallCsv" + ], + "eval_id": "bb6e0a4b-7faf-4aa6-a524-548cddbc2732", + "ground": { + "answer": "The correct amount spent on utilities.", + "eval": { + "type": "file" + }, + "files": [ + "output.txt" + ], + "should_contain": [ + "1861" + ] + }, + "info": { + "description": "Tests if the agent can answer a question from a csv", + "difficulty": "intermediate", + "side_effects": [ + "" + ] + }, + "name": "AnswerQuestionCsv", + "task": "How much was spent on utilities in total ? Write the answer in an output.txt file." +} |