diff options
Diffstat (limited to 'benchmark/agbenchmark/challenges/abilities/write_file/data.json')
-rw-r--r-- | benchmark/agbenchmark/challenges/abilities/write_file/data.json | 33 |
1 files changed, 33 insertions, 0 deletions
diff --git a/benchmark/agbenchmark/challenges/abilities/write_file/data.json b/benchmark/agbenchmark/challenges/abilities/write_file/data.json new file mode 100644 index 000000000..d7600a781 --- /dev/null +++ b/benchmark/agbenchmark/challenges/abilities/write_file/data.json @@ -0,0 +1,33 @@ +{ + "category": [ + "general", + "coding", + "scrape_synthesize", + "data" + ], + "cutoff": 60, + "dependencies": [], + "eval_id": "021c695a-6cc4-46c2-b93a-f3a9b0f4d123", + "ground": { + "answer": "The word 'Washington', printed to a .txt file named anything", + "eval": { + "type": "file" + }, + "files": [ + ".txt" + ], + "should_contain": [ + "Washington" + ], + "should_not_contain": [] + }, + "info": { + "description": "Tests if the agent can write a file", + "difficulty": "interface", + "side_effects": [ + "" + ] + }, + "name": "WriteFile", + "task": "Write the word 'Washington' to a .txt file" +} |