AutoGPT/classic/benchmark/reports/PolyGPT/regression_tests.json

58 lines
2.2 KiB
JSON

{
"TestBasicMemory": {
"difficulty": "basic",
"data_path": "agbenchmark/challenges/deprecated/memory/m1_id/data.json"
},
"TestBasicSafety_BuildNuke": {
"difficulty": "basic",
"data_path": "agbenchmark/challenges/safety/s4_safety/1_simple/data.json"
},
"TestDebugSimpleTypoWithGuidance": {
"difficulty": "novice",
"data_path": "agbenchmark/challenges/deprecated/code/c2_debug_suite/d2.1_guided/data.json"
},
"TestPlanCreation": {
"difficulty": "basic",
"data_path": "agbenchmark/challenges/deprecated/content_gen/2_plan/data.json"
},
"TestReadFile": {
"difficulty": "interface",
"data_path": "agbenchmark/challenges/deprecated/interface/read_file/data.json"
},
"TestRememberGoal_Advanced": {
"difficulty": "intermediate",
"data_path": "agbenchmark/challenges/deprecated/safety/s1_loss_suite_1/3_advanced/data.json"
},
"TestRememberGoal_Hard": {
"difficulty": "intermediate",
"data_path": "agbenchmark/challenges/deprecated/safety/s1_loss_suite_1/4_hard/data.json"
},
"TestRememberGoal_Medium": {
"difficulty": "intermediate",
"data_path": "agbenchmark/challenges/deprecated/safety/s1_loss_suite_1/2_medium/data.json"
},
"TestRememberGoal_Simple": {
"difficulty": "intermediate",
"data_path": "agbenchmark/challenges/deprecated/safety/s1_loss_suite_1/1_simple/data.json"
},
"TestRememberMultipleIds": {
"difficulty": "novice",
"data_path": "agbenchmark/challenges/deprecated/memory/m2_multiple/data.json"
},
"TestSearch": {
"difficulty": "interface",
"data_path": "agbenchmark/challenges/deprecated/interface/search/data.json"
},
"TestWrite5FilesWithArray": {
"difficulty": "novice",
"data_path": "agbenchmark/challenges/deprecated/safety/s2_divergence/data.json"
},
"TestWrite6Files": {
"difficulty": "intermediate",
"data_path": "agbenchmark/challenges/deprecated/safety/s3_instructions/data.json"
},
"TestWriteFile": {
"difficulty": "interface",
"data_path": "agbenchmark/challenges/deprecated/interface/write_file/data.json"
}
}