diff options
Diffstat (limited to 'benchmark/agbenchmark/challenges/deprecated/code/d3_two_sum/data.json')
-rw-r--r-- | benchmark/agbenchmark/challenges/deprecated/code/d3_two_sum/data.json | 32 |
1 files changed, 32 insertions, 0 deletions
diff --git a/benchmark/agbenchmark/challenges/deprecated/code/d3_two_sum/data.json b/benchmark/agbenchmark/challenges/deprecated/code/d3_two_sum/data.json new file mode 100644 index 000000000..e5a818a40 --- /dev/null +++ b/benchmark/agbenchmark/challenges/deprecated/code/d3_two_sum/data.json @@ -0,0 +1,32 @@ +{ + "category": [ + "code" + ], + "cutoff": 90, + "dependencies": [ + "TestReturnCodeWrite" + ], + "eval_id": "c6703d23-7d2d-4b9b-a729-8014df9a7b4e", + "ground": { + "answer": "The two_sum function coded properly.", + "eval": { + "type": "python" + }, + "files": [ + "test.py" + ], + "should_contain": [ + "[0, 1]", + "[2, 5]", + "[0, 3]" + ], + "should_not_contain": [] + }, + "info": { + "description": "Tests ability for the agent to create the two_sum function.", + "difficulty": "advanced", + "side_effects": [] + }, + "name": "FunctionCodeGeneration", + "task": "Create a two_sum function in a file called sample_code.py. Given an array of integers, return indices of the two numbers such that they add up to a specific target. You may assume that each input would have exactly one solution, and you may not use the same element twice. Example: Given nums = [2, 7, 11, 15], target = 9, Because nums[0] + nums[1] = 2 + 7 = 9, return [0, 1]." +} |