mirror of
https://github.com/aljazceru/Auto-GPT.git
synced 2026-01-31 11:54:30 +01:00
fix: Fixing Benchmarking
- Importing missing metadata field in Test class in report_types.py - Adding GAIA categories 1, 2, and 3 in data_types.py
This commit is contained in:
@@ -51,6 +51,8 @@ class Test(BaseModelBenchmark):
|
||||
category: List[str]
|
||||
task: str
|
||||
reached_cutoff: bool
|
||||
metadata: Any
|
||||
|
||||
|
||||
|
||||
class ReportBase(BaseModelBenchmark):
|
||||
@@ -68,6 +70,7 @@ class Report(ReportBase):
|
||||
tests: Dict[str, Test]
|
||||
|
||||
|
||||
|
||||
class ReportV2(Test, ReportBase):
|
||||
test_name: str
|
||||
run_id: str | None
|
||||
|
||||
@@ -174,6 +174,9 @@ class Category(str, Enum):
|
||||
GENERALIST = "general"
|
||||
CODING = "coding"
|
||||
SCRAPE_SYNTHESIZE = "scrape_synthesize"
|
||||
GAIA_1 = "GAIA_1"
|
||||
GAIA_2 = "GAIA_2"
|
||||
GAIA_3 = "GAIA_3"
|
||||
|
||||
|
||||
class ChallengeData(BaseModel):
|
||||
|
||||
Reference in New Issue
Block a user