Skip to content

armgit / fara

Public Imported from GitHub
0

Fara1.5 – A family of frontier computer use agent models

Update __init__.py

Corby Rossetb0030f7abe09
diff --git a/webeval/src/webeval/benchmarks/__init__.py b/webeval/src/webeval/benchmarks/__init__.py
index 5e4af93..fd92088 100644
--- a/webeval/src/webeval/benchmarks/__init__.py
+++ b/webeval/src/webeval/benchmarks/__init__.py
@@ -1,39 +1,9 @@
-# from .assistantbench.assistantbench import AssistantBenchBenchmark
-# from .custom.custom import CustomBenchmark
-# from .gaia.gaia import GaiaBenchmark
from .webvoyager.webvoyager import WebVoyagerBenchmark
-# from .mdm2w.mdm2w import MultimodalM2WBenchmark
-# from .aurora.aurora import AuroraBenchmark
from .om2w.om2w import OnlineM2WBenchmark
from .webtailbench.webtailbench import WebTailBenchBenchmark
-# from .holdout.holdout import HoldoutBenchmark
-# from .deepshop.deepshop import DeepShopBenchmark
-# from .browsecomp.browsecomp import BrowseCompBenchmark
-# from .screenspot.screenspot_v1 import ScreenspotV1Benchmark
-# from .screenspot.screenspot_v2 import ScreenspotV2Benchmark
-# from .screenspot.screenspot_pro import ScreenspotProBenchmark
-# from .instruction_following.instruction_following import InstructionFollowingBenchmark
-# from .instruction_following.agent_harm import AgentHarmBenchmark
-# from .instruction_following.visualwebbench_webqa import VisualWebBenchWebQA
-# from .realeval.realeval import RealEvalBenchmark
__all__ = [
- # "AssistantBenchBenchmark",
- # "CustomBenchmark",
- # "GaiaBenchmark",
"WebVoyagerBenchmark",
- # "MultimodalM2WBenchmark",
- # "AuroraBenchmark",
"OnlineM2WBenchmark",
- "WebTailBenchBenchmark",
- # "HoldoutBenchmark",
- # "DeepShopBenchmark",
- # "BrowseCompBenchmark",
- # "ScreenspotV1Benchmark",
- # "ScreenspotV2Benchmark",
- # "ScreenspotProBenchmark",
- # "InstructionFollowingBenchmark",
- # "AgentHarmBenchmark",
- # "VisualWebBenchWebQA",
- # "RealEvalBenchmark"
+ "WebTailBenchBenchmark"
]